© 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. 149486
    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
    trak
    -0.31
    Hop
    -0.28
    èĻļ
    -0.28
    Side
    -0.27
    åĨĻ
    -0.27
     Hop
    -0.27
    å¿ĥ
    -0.27
    è¡Ģ
    -0.27
    side
    -0.26
    hop
    -0.26
    POSITIVE LOGITS
     mandated
    0.29
    è¹Ļ
    0.28
    -addon
    0.28
    该éĻ¢
    0.27
    minster
    0.27
    -basket
    0.26
    ä¸Ģå¹´å¤ļ
    0.26
    úa
    0.25
    该项
    0.25
    åıĪèĥ½
    0.25
    Activations Density 2.391%

    No Known Activations

    This feature has no known activations.