© 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. 149296
    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
    detach
    -0.25
    ä¸į对
    -0.25
    _COMPAT
    -0.24
    NotSupportedException
    -0.24
     fier
    -0.23
    æĬ½è±¡
    -0.23
    ascus
    -0.23
     receipt
    -0.23
    ksam
    -0.23
    ateral
    -0.23
    POSITIVE LOGITS
    illet
    0.30
     backstage
    0.28
    ãģ¡ãģ¯
    0.26
    顶å±Ĥ
    0.26
    èĬĿ麻
    0.25
     tops
    0.24
    æĹłä¸į
    0.24
    deer
    0.24
    CW
    0.24
    åħĨ
    0.24
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.