© 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. 52511
    Prev
    Next
    INDEX
    Explanations

    gluten

    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
    -gr
    -0.31
    è°·
    -0.27
    æľįåĬ¡æ°´å¹³
    -0.26
     grain
    -0.26
    ä¹IJ
    -0.26
    åĬŁè¯¾
    -0.26
    橦
    -0.25
     Wäh
    -0.25
    溯æºIJ
    -0.25
    gow
    -0.25
    POSITIVE LOGITS
     development
    0.27
    ettes
    0.26
     tem
    0.26
    urement
    0.25
    heets
    0.25
    LBL
    0.25
     Development
    0.25
    æĻķ
    0.25
     kol
    0.25
    ove
    0.24
    Activations Density 0.010%

    No Known Activations