© 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. 64413
    Prev
    Next
    INDEX
    Explanations

    patent/invention descriptions

    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
     Axis
    -0.31
    atos
    -0.29
    yard
    -0.28
    æѤäºĭ
    -0.28
    è¿Ļäºĭ
    -0.28
    -axis
    -0.27
    loid
    -0.26
    Axis
    -0.26
    _axis
    -0.25
    aston
    -0.24
    POSITIVE LOGITS
    ores
    0.29
     Survivor
    0.27
    *((
    0.24
    VERS
    0.24
    ['__
    0.24
    ffc
    0.24
    mis
    0.24
    [NUM
    0.24
    æĮĩ
    0.24
     Meadows
    0.24
    Activations Density 76.298%

    No Known Activations