© 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. 33-TRANSCODER-HP
    7. 52518
    Prev
    Next
    INDEX
    Explanations

    light beams and lasers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Creek
    -0.29
    еÑĢÑĤ
    -0.28
    globals
    -0.28
    idders
    -0.27
    .twig
    -0.26
     Casting
    -0.25
    æ°´æµģ
    -0.24
    Streaming
    -0.24
    æĺ¯ä¸Ģ家
    -0.24
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.24
    POSITIVE LOGITS
    -b
    0.27
    енÑĤ
    0.27
    ib
    0.27
     cont
    0.27
     col
    0.26
     Nich
    0.26
    orm
    0.25
     con
    0.25
    ues
    0.25
     кол
    0.25
    Activations Density 0.038%

    No Known Activations