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. 72482
    Prev
    Next
    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    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
    Chuck
    -0.08
    重磅
    -0.08
    펑
    -0.07
    REDIS
    -0.07
    훗
    -0.07
    .setTitle
    -0.07
    튜
    -0.07
    אולי
    -0.06
    _suspend
    -0.06
    SendMessage
    -0.06
    POSITIVE LOGITS
     legion
    0.07
     bare
    0.07
    iliary
    0.07
     crow
    0.07
    things
    0.07
     adorned
    0.07
    /components
    0.06
     Collective
    0.06
    oppers
    0.06
    atic
    0.06
    Activations Density 0.045%

    No Known Activations