© 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. 129446
    Prev
    Next
    INDEX
    Explanations

    Code and identifiers

    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¿ĺ好
    -0.30
     alike
    -0.28
    matchCondition
    -0.28
    avax
    -0.27
     serialVersionUID
    -0.27
    ä¸įå¤Ł
    -0.27
    engers
    -0.26
    ŀĭ
    -0.26
    ayers
    -0.25
    Remarks
    -0.25
    POSITIVE LOGITS
    .Marker
    0.28
     proven
    0.28
    inator
    0.27
    便åĪ©
    0.27
     bigot
    0.26
    omite
    0.26
    stick
    0.26
     quÃł
    0.26
    ongan
    0.25
    éĽĨå¸Ĥ
    0.25
    Activations Density 9.583%

    No Known Activations