© 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. 23529
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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
    _toggle
    -0.30
    Toggle
    -0.27
    Gate
    -0.26
    æ²³æµģåŁŁ
    -0.26
    æĮĩæķ°
    -0.26
    sist
    -0.25
    å¾Ģå¾Ģæĺ¯
    -0.25
     Gate
    -0.25
    å®ļéĩı
    -0.24
    éķ¿è¾Ī
    -0.24
    POSITIVE LOGITS
    dek
    0.29
     overhead
    0.27
    æīĭæĦŁ
    0.26
     operations
    0.26
     appeal
    0.26
    Extent
    0.25
     liqu
    0.25
     assim
    0.25
     degrees
    0.24
     material
    0.24
    Activations Density 0.001%

    No Known Activations