© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 70930
    Prev
    Next
    INDEX
    Explanations

    discourse markers that structure formal writing—phrases signaling examples, enumeration, attribution, or emphasis (e.g., “for example,” “first,” “according to,” “is one of”).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ordinal
    -0.07
    เขต
    -0.07
    أسم
    -0.07
    .)↵↵↵↵
    -0.07
     okreś
    -0.07
    שלם
    -0.07
     Disp
    -0.07
    .↵↵↵
    -0.06
     scarce
    -0.06
    著作權
    -0.06
    POSITIVE LOGITS
     RECE
    0.07
     avanz
    0.07
    嶝
    0.07
    と考え
    0.07
    ruby
    0.07
    quared
    0.07
     Massive
    0.07
    includes
    0.07
     друзья
    0.06
     onTouch
    0.06
    Activations Density 0.460%

    No Known Activations