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. 19-RESID-POST-AA
    6. 130759
    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ຊ
    -0.07
    $ar
    -0.07
    Ứ
    -0.07
    ję
    -0.07
    Posts
    -0.07
    .UserId
    -0.06
     ARP
    -0.06
     Emails
    -0.06
    (Il
    -0.06
    شغل
    -0.06
    POSITIVE LOGITS
    Located
    0.08
    뎬
    0.07
     peak
    0.07
     linewidth
    0.07
    搌
    0.06
    [in
    0.06
     embodied
    0.06
    -encoded
    0.06
    廋
    0.06
    èle
    0.06
    Activations Density 0.110%

    No Known Activations