© 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. 22-TRANSCODER-HP
    7. 130362
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibli
    -0.25
     elic
    -0.25
     litt
    -0.25
     {?
    -0.25
     dict
    -0.24
    ?',
    -0.24
    ucci
    -0.24
    롱
    -0.23
    etter
    -0.23
     Het
    -0.23
    POSITIVE LOGITS
     ancestor
    0.25
    åĢŁ
    0.25
     ancest
    0.25
     trough
    0.25
    å®ĥæĺ¯
    0.25
    å®ĥ
    0.24
    Past
    0.23
     bpp
    0.23
    让å®ĥ
    0.23
    gst
    0.23
    Activations Density 0.026%

    No Known Activations