© 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. 41106
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
    çĭ¸
    -0.25
     signals
    -0.25
     Levy
    -0.24
    åħħ
    -0.24
     acid
    -0.24
    æ©¡
    -0.24
    ç«ĭæĸ¹
    -0.24
     staging
    -0.24
    è¡¥
    -0.23
     rein
    -0.23
    POSITIVE LOGITS
    ies
    0.31
    ise
    0.30
    yny
    0.28
    еÑģÑģ
    0.27
    fcc
    0.27
    å²Ľ
    0.26
    isters
    0.26
    KA
    0.26
    uess
    0.26
    ises
    0.26
    Activations Density 0.001%

    No Known Activations