© 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. 12-TRANSCODER-HP
    7. 23052
    Prev
    Next
    INDEX
    Explanations

    Pigeons and "dov"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikan
    -0.33
     Composition
    -0.31
     edited
    -0.31
    lectic
    -0.29
     editing
    -0.29
     Editing
    -0.29
    Composition
    -0.29
    undry
    -0.29
    ç»ĦæĪIJ
    -0.28
    åĵģç§į
    -0.28
    POSITIVE LOGITS
    åĢ¾
    0.27
    æ®ĭ
    0.27
     turns
    0.26
    _residual
    0.25
     residuals
    0.25
     windows
    0.25
    rink
    0.24
    èĢģå¸ĪçļĦ
    0.24
    举
    0.24
    ign
    0.24
    Activations Density 0.006%

    No Known Activations