© 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. 151448
    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
    Negative Logits
    å·½
    -0.27
    è·ijäºĨ
    -0.26
    ière
    -0.26
     impuls
    -0.25
    俸
    -0.25
    æģ¯
    -0.25
     Eth
    -0.24
     Heat
    -0.24
     federally
    -0.24
    人寿
    -0.24
    POSITIVE LOGITS
    _matching
    0.25
    iec
    0.24
    -extra
    0.24
    å¼Ģåı£
    0.24
    èĵī
    0.23
    æĥĬå¥ĩ
    0.23
     conditioning
    0.23
    dziaÅĤ
    0.23
    åIJĦ项
    0.23
    .fm
    0.23
    Activations Density 0.679%

    No Known Activations

    This feature has no known activations.