© 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. 20-TRANSCODER-HP
    7. 108268
    Prev
    Next
    INDEX
    Explanations

    roles/jobs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJįåı«
    -0.33
    åı«åģļ
    -0.32
    åĪĨåĪ«æĺ¯
    -0.31
    åij½åIJį为
    -0.28
    åĪĨåĪ«ä¸º
    -0.28
     ÐĶм
    -0.27
     named
    -0.27
    åı«
    -0.27
    _SUPPLY
    -0.27
     namely
    -0.26
    POSITIVE LOGITS
     VIN
    0.25
    uring
    0.25
     Shooting
    0.24
    èĨ³
    0.24
    ä¸Ģ线
    0.24
    หาร
    0.24
    GOR
    0.23
     "...
    0.23
    ustry
    0.23
     STAR
    0.23
    Activations Density 28.172%

    No Known Activations