Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130717
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Debugf
    -0.07
    ags
    -0.07
     ↵        ↵
    -0.06
    擅自
    -0.06
    สำห
    -0.06
    =utf
    -0.06
    .slf
    -0.06
     прежде
    -0.06
    ⵣ
    -0.06
     הזכ
    -0.06
    POSITIVE LOGITS
     thinner
    0.08
    _Var
    0.08
    placeholders
    0.07
     Und
    0.07
     ether
    0.07
    飯
    0.07
    _main
    0.07
     Monkey
    0.07
     économique
    0.07
    殉
    0.07
    Activations Density 0.001%

    No Known Activations