© 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. 30-TRANSCODER-HP
    7. 95715
    Prev
    Next
    INDEX
    Explanations

    new roles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     positions
    -0.29
     Positions
    -0.29
    社ä¼ļèµĦæľ¬
    -0.28
     Position
    -0.28
    linky
    -0.27
    åŃ¢
    -0.26
    èIJ¥åķĨçݯå¢ĥ
    -0.25
    atomy
    -0.25
    çĥŁçģ«
    -0.25
    aceutical
    -0.25
    POSITIVE LOGITS
     office
    0.33
    åĬŀåħ¬
    0.31
    大纲
    0.29
    åĿIJ
    0.29
    SH
    0.29
    idelity
    0.28
    æĪIJæķĪ
    0.28
    åĬ¡
    0.28
    office
    0.28
     plane
    0.28
    Activations Density 0.885%

    No Known Activations