© 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. 20-TRANSCODER-HP
    7. 130960
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, dates, filenames

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Completely
    -0.26
    è£ĺ
    -0.26
     reversible
    -0.25
    oodle
    -0.25
     Leh
    -0.24
     vern
    -0.24
    ä¹Łä¸įçŁ¥éģĵ
    -0.24
     гаÑĢ
    -0.23
     Protective
    -0.23
    äºĨ解åĪ°
    -0.23
    POSITIVE LOGITS
    pic
    0.27
    compass
    0.27
    oric
    0.26
    ç
    0.25
    rens
    0.25
    köp
    0.24
    ivar
    0.24
    èĢ»
    0.23
    erc
    0.23
     thereafter
    0.23
    Activations Density 7.351%

    No Known Activations