© 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. 25630
    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
    gressive
    -0.28
    hol
    -0.26
     hol
    -0.25
    çŃīå½¢å¼ı
    -0.25
    nesty
    -0.25
    æĹ¶ä»£ä¸ŃåĽ½
    -0.25
    look
    -0.24
    uiltin
    -0.24
    åĪ¶åº¦æĶ¹éĿ©
    -0.24
    gression
    -0.24
    POSITIVE LOGITS
    ZE
    0.28
    -current
    0.27
     Doctors
    0.25
     costing
    0.24
     Low
    0.24
     Jobs
    0.24
    ä½İæĪIJæľ¬
    0.23
    atron
    0.23
     yaptı
    0.23
    ropp
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.