© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 151131
    Prev
    Next
    INDEX
    Explanations

    boot or bootstrap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gele
    -0.25
    tle
    -0.25
     MOTOR
    -0.25
    IOD
    -0.25
     inverted
    -0.24
     jo
    -0.24
     uncovered
    -0.23
    chas
    -0.23
     Formula
    -0.23
    urnished
    -0.23
    POSITIVE LOGITS
    leg
    0.32
    /bootstrap
    0.28
    LEG
    0.27
    classpath
    0.26
    ateg
    0.26
     Bootstrap
    0.26
    legs
    0.25
     Russell
    0.25
    -loader
    0.25
    loader
    0.25
    Activations Density 1.235%

    No Known Activations