© 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. 54353
    Prev
    Next
    INDEX
    Explanations

    requests for exhaustive, in-depth, step-by-step analyses or guides with heavy meta-instructional phrasing and emphasis on thoroughness and detail.

    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
    ifiers
    -0.07
     просто
    -0.06
    >O
    -0.06
    ઉ
    -0.06
     сразу
    -0.06
     counties
    -0.06
    -0.06
    되고
    -0.06
     souvenir
    -0.06
     CN
    -0.06
    POSITIVE LOGITS
     tras
    0.07
     pared
    0.07
    -placeholder
    0.07
    (src
    0.07
    맵
    0.07
    CKER
    0.07
    颊
    0.07
    点评
    0.07
     yPos
    0.06
    bilit
    0.06
    Activations Density 0.112%

    No Known Activations