© 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. 32-TRANSCODER-HP
    7. 44066
    Prev
    Next
    INDEX
    Explanations

    technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æł¼å°Ķ
    -0.31
     biased
    -0.25
    alo
    -0.25
     bleach
    -0.25
     Clair
    -0.24
    Alan
    -0.24
    toMatchSnapshot
    -0.23
    æ¼ī
    -0.23
     yyn
    -0.23
    clo
    -0.23
    POSITIVE LOGITS
    çļĦæĪIJæľ¬
    0.31
    æĭ³
    0.28
    (cost
    0.27
    æ³ķè§Ħ
    0.26
    ä¾
    0.26
    osome
    0.26
    annes
    0.25
    bre
    0.25
     Peb
    0.25
    æľ¬ç½ijç«Ļ
    0.25
    Activations Density 0.000%

    No Known Activations