© 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. 64417
    Prev
    Next
    INDEX
    Explanations

    Code and licenses

    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
    è··
    -0.28
    éĿ¡
    -0.26
    eras
    -0.26
    rike
    -0.25
    ä¸Ńä»ĭ
    -0.24
    marks
    -0.24
    rikes
    -0.24
    manufacturer
    -0.24
     mechanically
    -0.24
     maxHeight
    -0.24
    POSITIVE LOGITS
    toast
    0.28
    zew
    0.25
    人们对
    0.25
    人
    0.24
    eus
    0.24
    /ay
    0.24
    åIJĦåĮº
    0.23
     plut
    0.23
    eming
    0.23
    acci
    0.23
    Activations Density 0.217%

    No Known Activations