© 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. 8499
    Prev
    Next
    INDEX
    Explanations

    gu

    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
    system
    -0.30
    äºĨä¸Ģåľº
    -0.30
     eth
    -0.27
    bolt
    -0.26
    sure
    -0.26
     pl
    -0.25
     writ
    -0.25
    éĻIJãĤĬ
    -0.25
    .Headers
    -0.25
     enc
    -0.24
    POSITIVE LOGITS
    ese
    0.28
    icter
    0.26
    istan
    0.25
    itchens
    0.25
    phas
    0.25
     Pharm
    0.24
    注æĺİæĿ¥æºIJ
    0.24
    åĴ¨è¯¢æľįåĬ¡
    0.24
    cess
    0.23
     underestimated
    0.23
    Activations Density 0.029%

    No Known Activations