© 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. 23685
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
    åĩºåĬ¨
    -0.29
     envi
    -0.26
    á»ij
    -0.25
    nos
    -0.25
    bras
    -0.24
     Brooks
    -0.24
    quate
    -0.24
    ãĥ¼ãĤ·
    -0.23
    brace
    -0.23
    azine
    -0.23
    POSITIVE LOGITS
    cci
    0.29
    ivo
    0.29
    ronic
    0.28
     Elo
    0.27
    rible
    0.26
     yan
    0.26
     nowhere
    0.26
    oley
    0.25
    ivar
    0.25
    iking
    0.24
    Activations Density 0.001%

    No Known Activations