© 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. 35-TRANSCODER-HP
    7. 40758
    Prev
    Next
    INDEX
    Explanations

    H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Builders
    -0.28
    manship
    -0.28
    enburg
    -0.27
    mé
    -0.25
    ivor
    -0.25
    nesc
    -0.25
    pectives
    -0.24
    bet
    -0.24
    filer
    -0.24
    iliate
    -0.23
    POSITIVE LOGITS
    åĪĨéĴŁåIJİ
    0.30
    angi
    0.27
    uz
    0.27
    gra
    0.26
    æݸ
    0.26
     ocas
    0.26
     Ug
    0.26
     Olymp
    0.26
     sik
    0.25
    zw
    0.25
    Activations Density 13.327%

    No Known Activations