© 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. 44248
    Prev
    Next
    INDEX
    Explanations

    date

    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
    lds
    -0.29
    ATOR
    -0.27
    çļĦèĥĮåIJİ
    -0.27
    att
    -0.27
    loh
    -0.26
    jun
    -0.26
     jumping
    -0.26
     earth
    -0.25
    amon
    -0.25
    col
    -0.24
    POSITIVE LOGITS
    eat
    0.31
    dera
    0.27
    è¡į
    0.27
    ei
    0.26
    çŁ³èĨı
    0.26
    еÑģÑĮ
    0.25
    dish
    0.25
    avors
    0.25
    دÙħ
    0.25
    éĹªéĹª
    0.24
    Activations Density 0.003%

    No Known Activations