© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 127086
    Prev
    Next
    INDEX
    Explanations

    Assistant

    np_max-act · gemini-2.0-flash

    the assistant role marker at the start of an assistant response in chat-style transcripts.

    oai_token-act-pair · gpt-5
    Triggered 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
    Negative Logits
     squares
    -0.07
     Inn
    -0.07
     grave
    -0.07
     Laurent
    -0.07
     logistic
    -0.07
     Http
    -0.07
     ביח
    -0.07
    .connector
    -0.07
     configur
    -0.07
     Appears
    -0.07
    POSITIVE LOGITS
    ŵ
    0.07
    侍
    0.07
    茹
    0.07
    .Diagnostics
    0.07
    糁
    0.07
    _recommend
    0.06
    提议
    0.06
    stri
    0.06
    锿
    0.06
    داخل
    0.06
    Activations Density 0.120%

    No Known Activations