© 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. 63260
    Prev
    Next
    INDEX
    Explanations

    editor

    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
     Bundy
    -0.26
    operative
    -0.24
     punch
    -0.24
    arak
    -0.24
     COPYING
    -0.23
     Including
    -0.23
    VEC
    -0.23
     côté
    -0.23
    ileged
    -0.23
    akis
    -0.23
    POSITIVE LOGITS
    bay
    0.27
     (£
    0.26
    ä»ĸ们éĥ½
    0.25
    orate
    0.24
    åĩłæŃ¥
    0.24
    tle
    0.23
    HAND
    0.23
    ãĥĬãĥ¼
    0.23
    鲤
    0.23
    rx
    0.23
    Activations Density 11.236%

    No Known Activations