© 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. 25355
    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
    çŀŃ解並
    -0.28
    使çĶ¨ç¶²è·¯
    -0.28
    纳æĸ¯
    -0.26
    ä¸įå¼Ģ
    -0.26
     MERCHANTABILITY
    -0.26
     MediaTek
    -0.26
    GetPosition
    -0.25
    (trim
    -0.25
    ä¸įå¾Ĺ转载
    -0.25
     punches
    -0.25
    POSITIVE LOGITS
    note
    0.35
    in
    0.32
     way
    0.31
    und
    0.31
     simply
    0.30
    n
    0.30
     Statistics
    0.29
    no
    0.29
     If
    0.28
    step
    0.28
    Activations Density 0.067%

    No Known Activations

    This feature has no known activations.