© 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. 24-TRANSCODER-HP
    7. 150637
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĥ½è§īå¾Ĺ
    -0.28
    .setTitle
    -0.26
    æĸĻ
    -0.26
    åī²
    -0.25
    |%
    -0.25
    æIJĵ
    -0.25
    기ëĬĶ
    -0.25
    ç¬ijè¯Ŀ
    -0.24
     Percentage
    -0.24
    è¿ĽæŃ¥
    -0.24
    POSITIVE LOGITS
    ÅĽnie
    0.26
     rer
    0.24
    alyzer
    0.24
    Ä°R
    0.24
    ragen
    0.24
    ivate
    0.24
    iete
    0.23
     consistent
    0.23
    DMI
    0.23
    ctors
    0.23
    Activations Density 1.261%

    No Known Activations

    This feature has no known activations.