© 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. 149163
    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
     gdy
    -0.28
    "Don
    -0.26
    eme
    -0.25
    æŀ¶
    -0.25
    kish
    -0.25
    åĩºçİ°åľ¨
    -0.24
     ì¶
    -0.24
    ä½ı
    -0.24
    ç½ijç«Ļé¦ĸ页
    -0.24
     ".
    -0.24
    POSITIVE LOGITS
    SAVE
    0.27
    .responseText
    0.26
     rehears
    0.25
     saves
    0.25
    ĵį
    0.25
    itemid
    0.24
    hev
    0.24
    _coeffs
    0.24
    çĭ¬çī¹çļĦ
    0.24
    åĩŃ
    0.24
    Activations Density 0.297%

    No Known Activations

    This feature has no known activations.