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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 56847
    Prev
    Next
    INDEX
    Explanations

    ard

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .textContent
    -0.07
    yw
    -0.07
    ,E
    -0.06
    Advance
    -0.06
    国有企业
    -0.06
    Injection
    -0.06
     zf
    -0.06
    ᐊ
    -0.06
    레
    -0.06
    的日子里
    -0.06
    POSITIVE LOGITS
    합
    0.08
     strncpy
    0.07
    附加值
    0.07
     删除
    0.07
     ComVisible
    0.07
     suspend
    0.07
    前述
    0.07
     COUNTY
    0.07
     vX
    0.06
     Rugby
    0.06
    Activations Density 0.002%

    No Known Activations