© 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. 27-TRANSCODER-HP
    7. 9329
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľīæľŁ
    -0.29
    ellig
    -0.26
    añ
    -0.25
    ä¸ĢåĪĨ
    -0.25
    actual
    -0.25
    amins
    -0.25
    jure
    -0.24
    æł¹æľ¬å°±ä¸į
    -0.24
    jsc
    -0.24
    TRL
    -0.24
    POSITIVE LOGITS
    åIJ¦åĪĻ
    0.31
     ÑĩÑĤ
    0.30
    åIJ¦åīĩ
    0.28
    Otherwise
    0.27
    ç½Ķ
    0.27
     Otherwise
    0.26
    ãģ¡ãĤĥãĤĵ
    0.26
    çļĦ责任
    0.26
     guilty
    0.26
    éĻ
    0.26
    Activations Density 0.004%

    No Known Activations