© 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. 22-TRANSCODER-HP
    7. 131044
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç³ķ
    -0.26
    -console
    -0.26
    å¸ĮèħĬ
    -0.25
    é«ĺåĩº
    -0.25
    ToLeft
    -0.25
    å¤ļãģĦ
    -0.25
    affles
    -0.25
    ä¸Ģè½®
    -0.24
     Orig
    -0.24
     Blade
    -0.23
    POSITIVE LOGITS
    also
    0.37
    ä¹Ł
    0.35
     also
    0.35
    缸åºĶ
    0.35
    ä¹Łå°±
    0.34
     CÅ©ng
    0.32
    ä¹Łåľ¨
    0.31
    缸åºĶçļĦ
    0.31
    åIJĮæĹ¶ä¹Ł
    0.31
    ä¹Łä¸º
    0.30
    Activations Density 0.006%

    No Known Activations