© 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. 29814
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ä¿Ŀå®Ī
    -0.27
    ubbles
    -0.27
     chase
    -0.27
     impact
    -0.26
    æķ¢
    -0.26
    instrument
    -0.24
     Hughes
    -0.24
    æģķ
    -0.24
    èĪĮ
    -0.24
    جÙĦ
    -0.24
    POSITIVE LOGITS
    vern
    0.32
    æŃ¢ãĤģ
    0.28
    lep
    0.26
    imentos
    0.26
    çݩ家们
    0.25
    rie
    0.25
    æĪĺåľº
    0.25
     xuá»ijng
    0.25
    eries
    0.24
    atório
    0.24
    Activations Density 2.436%

    No Known Activations