© 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. 130545
    Prev
    Next
    INDEX
    Explanations

    race

    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
    çĽĬ
    -0.28
    è¶Ĭ
    -0.27
    sis
    -0.26
    sit
    -0.26
    ryption
    -0.26
    flu
    -0.24
    edd
    -0.24
     Pain
    -0.24
    .newLine
    -0.24
    eor
    -0.24
    POSITIVE LOGITS
    ipel
    0.31
    ä¸İä¸ŃåĽ½
    0.29
    ivities
    0.27
    ady
    0.26
     Chavez
    0.25
     sodom
    0.25
    _tex
    0.24
    对ä¸ŃåĽ½
    0.24
    -columns
    0.24
     quem
    0.23
    Activations Density 7.054%

    No Known Activations