© 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. 41188
    Prev
    Next
    INDEX
    Explanations

    local

    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
    Not in Any Lists

    No Comments

    Negative Logits
    caffold
    -0.27
    èĮ¬
    -0.26
     anch
    -0.25
    éĸ±
    -0.25
    éĢ¾
    -0.24
    OSH
    -0.24
     crem
    -0.24
    éħ¸å¥¶
    -0.24
    ä¸įå°ijäºİ
    -0.24
    pos
    -0.23
    POSITIVE LOGITS
    轻轻
    0.28
    åĪĨ解
    0.26
    åħīèį£
    0.25
    лег
    0.24
    orer
    0.24
    adero
    0.24
    ester
    0.23
    lore
    0.23
    SF
    0.23
    éģĹæ¼ı
    0.23
    Activations Density 0.001%

    No Known Activations