© 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. 111301
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.28
     abuses
    -0.26
     def
    -0.26
     Roman
    -0.25
    å±ĭ
    -0.24
     proven
    -0.24
    rove
    -0.24
    æĹ¶è¡¨ç¤º
    -0.23
    æľ¬ç«Ļ
    -0.23
    ŀĭ
    -0.23
    POSITIVE LOGITS
    ocide
    0.28
    arios
    0.25
    hone
    0.25
    æīĭä¸Ĭ
    0.24
    ¢åįķ
    0.24
    ")+
    0.24
    åħ¨åĬĽä»¥
    0.24
    urgy
    0.24
    ç´§å¼ł
    0.24
    optic
    0.23
    Activations Density 0.004%

    No Known Activations