© 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. 129641
    Prev
    Next
    INDEX
    Explanations

    Circuits and references

    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
    主æŨ
    -0.26
    inate
    -0.25
    ç§ijåѦæĬĢæľ¯
    -0.25
    udder
    -0.25
    enn
    -0.25
    _Selected
    -0.24
    ystone
    -0.24
     called
    -0.24
    cluded
    -0.24
    udios
    -0.23
    POSITIVE LOGITS
    á´Ħ
    0.27
     spy
    0.25
    MARY
    0.24
    ancia
    0.24
    amma
    0.24
     ÑģвÑıз
    0.24
    avar
    0.24
    omas
    0.23
    comparison
    0.23
    avra
    0.23
    Activations Density 18.259%

    No Known Activations