© 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. 23-TRANSCODER-HP
    7. 23375
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĹ¶ä»£ä¸ŃåĽ½
    -0.32
    apons
    -0.28
    anship
    -0.26
    Binder
    -0.26
    ±Ð¾ÑĤ
    -0.25
     materially
    -0.25
    .setResult
    -0.25
    hani
    -0.25
    xFFFFFF
    -0.24
     binding
    -0.24
    POSITIVE LOGITS
    O
    0.33
    vern
    0.29
     news
    0.28
    code
    0.27
     code
    0.27
    anc
    0.27
    med
    0.26
    view
    0.26
    away
    0.26
     Vor
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.