© 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. 151401
    Prev
    Next
    INDEX
    Explanations

    Code-related texts

    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
    Negative Logits
    kit
    -0.29
    icom
    -0.29
    æł·æĿ¿
    -0.27
     harmonic
    -0.27
     outbreak
    -0.27
     abusive
    -0.26
     Harmon
    -0.26
    opsis
    -0.26
    æł·çļĦ
    -0.26
    har
    -0.25
    POSITIVE LOGITS
     squares
    0.30
    lags
    0.29
    æ°´æµģ
    0.26
     granularity
    0.26
    ForeColor
    0.25
    åħĪæĬĬ
    0.25
    é¦ĸä½į
    0.25
     caul
    0.25
    çłĶ究æĪIJæŀľ
    0.25
    locked
    0.25
    Activations Density 0.962%

    No Known Activations