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. 6926
    Prev
    Next
    INDEX
    Explanations

    6

    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
    年由盛
    -0.07
    赞成
    -0.07
    .diff
    -0.07
    [label
    -0.07
     podrá
    -0.07
    的支持
    -0.07
     PQ
    -0.07
     properly
    -0.07
     Wien
    -0.07
    >/',
    -0.07
    POSITIVE LOGITS
     southwest
    0.07
    .pivot
    0.07
    _IRQ
    0.07
    ⛸
    0.06
     IDisposable
    0.06
    empresa
    0.06
    긱
    0.06
     Eth
    0.06
     Fort
    0.06
    刖
    0.06
    Activations Density 0.002%

    No Known Activations