© 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. 7985
    Prev
    Next
    INDEX
    Explanations

    Requesting more information

    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
    åľ¨ä»ĸ
    -0.28
    åľ¨åħ¶
    -0.28
    slider
    -0.26
    ç©Ĩ
    -0.26
    ’acc
    -0.26
    ibrator
    -0.26
    æ»ij
    -0.25
    åľ¨ä»ĸçļĦ
    -0.25
    è®°èĢħ表示
    -0.24
    éĹŃ
    -0.24
    POSITIVE LOGITS
    ROC
    0.27
    izen
    0.26
    asons
    0.26
     freely
    0.26
    Lake
    0.24
     consciously
    0.24
    (gs
    0.24
     anonymously
    0.24
    won
    0.23
    sockets
    0.23
    Activations Density 0.023%

    No Known Activations