© 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. 119057
    Prev
    Next
    INDEX
    Explanations

    Job departure

    np_max-act · gemini-2.0-flash
    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
     esse
    -0.07
     труд
    -0.07
    ，默认
    -0.07
     noen
    -0.06
    getc
    -0.06
    ṱ
    -0.06
    重要内容
    -0.06
     Addition
    -0.06
    他认为
    -0.06
    .DO
    -0.06
    POSITIVE LOGITS
     Pret
    0.07
     אותן
    0.07
    -W
    0.07
    _sampler
    0.07
    �
    0.07
    凌晨
    0.07
    怦
    0.07
    IFE
    0.07
    狠狠
    0.07
    -f
    0.07
    Activations Density 0.112%

    No Known Activations