© 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. 151076
    Prev
    Next
    INDEX
    Explanations

    cler

    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
    a
    -0.65
    i
    -0.57
    o
    -0.52
    er
    -0.50
    e
    -0.48
    en
    -0.46
    A
    -0.44
    aic
    -0.42
    al
    -0.42
    es
    -0.41
    POSITIVE LOGITS
    tempts
    0.37
    imately
    0.30
    istrar
    0.29
    ossal
    0.29
    itionally
    0.29
    gether
    0.28
    lectual
    0.28
     Pradesh
    0.27
    maal
    0.25
    ../../
    0.25
    Activations Density 1.873%

    No Known Activations