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. 2554
    Prev
    Next
    INDEX
    Explanations

    altitude/geography

    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
     Dr
    -0.08
    当地时间
    -0.07
     governments
    -0.07
     uz
    -0.06
    .framework
    -0.06
    utr
    -0.06
     vetor
    -0.06
    _reordered
    -0.06
     u
    -0.06
     recyclerView
    -0.06
    POSITIVE LOGITS
    els
    0.07
    감
    0.07
    .Contact
    0.07
    (age
    0.07
    age
    0.07
    皑
    0.07
    .language
    0.06
     Melanie
    0.06
    ┼
    0.06
    .Plugin
    0.06
    Activations Density 0.021%

    No Known Activations