© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107674
    Prev
    Next
    INDEX
    Explanations

    each or every

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oding
    -0.26
    —are
    -0.26
     strongest
    -0.26
    人éĥ½
    -0.26
    -'
    -0.26
    .'
    -0.25
     applicant
    -0.24
    .'"
    -0.24
    èŀ«
    -0.24
    eland
    -0.23
    POSITIVE LOGITS
    夹
    0.28
    æĭ¬
    0.26
    ált
    0.25
    _acl
    0.24
    rated
    0.24
    ogenic
    0.24
    _Model
    0.24
    模åŀĭ
    0.24
     crédito
    0.24
    ActionResult
    0.24
    Activations Density 0.119%

    No Known Activations