© 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. 23632
    Prev
    Next
    INDEX
    Explanations

    fashion

    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
    ernes
    -0.28
    [__
    -0.28
    ython
    -0.26
     outliers
    -0.25
     ì§
    -0.25
    ONA
    -0.25
     Kahn
    -0.24
    ::-
    -0.24
    .addWidget
    -0.24
    Operand
    -0.24
    POSITIVE LOGITS
    è¿ĺæľī
    0.31
    åıĸå¾Ĺ
    0.29
    æĮģ
    0.27
    adle
    0.27
    unas
    0.27
    asse
    0.27
    è¿ĺè¦ģ
    0.27
    è¿ĺéľĢè¦ģ
    0.27
    è¿ĺéľĢ
    0.26
    urat
    0.25
    Activations Density 0.010%

    No Known Activations