© 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. 23386
    Prev
    Next
    INDEX
    Explanations

    your/my

    np_max-act · gemini-2.0-flash
    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
    afia
    -0.27
    .jwt
    -0.27
    åĽ½å®¶çº§
    -0.26
    容
    -0.26
    æľĢ大ç¨ĭ度
    -0.26
    åIJĪçIJĨ
    -0.26
    æľĢé«ĺ
    -0.26
    .bind
    -0.25
     Burgess
    -0.25
    åħģ
    -0.25
    POSITIVE LOGITS
    hält
    0.27
     divers
    0.26
     managed
    0.26
    icolor
    0.25
    çļĦçħ§çīĩ
    0.24
     disposed
    0.24
     doubted
    0.24
    è¿Ļå¼ł
    0.24
    åij½
    0.23
    CDF
    0.23
    Activations Density 0.002%

    No Known Activations