© 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. 9-TRANSCODER-HP
    7. 29923
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bart
    -0.30
    åı¦ä¸ĢåįĬ
    -0.29
    çľĭçĤ¹
    -0.28
     unp
    -0.26
     icy
    -0.25
    æ¹ĸåĮº
    -0.25
    ä¸ī家
    -0.24
     паÑĢÑĤ
    -0.24
    fäh
    -0.24
     Lot
    -0.24
    POSITIVE LOGITS
    issen
    0.29
    ossal
    0.26
    èµ°
    0.26
    wf
    0.25
    atica
    0.25
    ä¸Ĭä¸ĭ游
    0.25
    .pid
    0.25
     наÑĤÑĥÑĢалÑĮн
    0.25
    nown
    0.25
    _malloc
    0.24
    Activations Density 0.940%

    No Known Activations