© 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. 19-TRANSCODER-HP
    7. 9042
    Prev
    Next
    INDEX
    Explanations

    common, share

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻ©
    -0.29
    éļª
    -0.28
    ľ
    -0.26
     erle
    -0.26
    设计åĻ¨
    -0.26
    æŶ任
    -0.26
    лÑĮн
    -0.26
    çļĦä¼łç»Ł
    -0.25
    ting
    -0.24
    赶ä¸Ĭ
    -0.24
    POSITIVE LOGITS
    sed
    0.27
    èĭ±
    0.27
     sob
    0.26
    sum
    0.25
     consist
    0.25
    éĩįä¸Ń
    0.24
     Alban
    0.24
    ded
    0.24
    herit
    0.23
     Cel
    0.23
    Activations Density 0.154%

    No Known Activations