© 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. 27-TRANSCODER-HP
    7. 56582
    Prev
    Next
    INDEX
    Explanations

    Code/Technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ouch
    -0.33
    GOOD
    -0.27
    å¥
    -0.26
    饰
    -0.26
     accomplished
    -0.25
     reduction
    -0.25
    addy
    -0.24
    éļ¾æĢª
    -0.24
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    -0.23
     dangling
    -0.23
    POSITIVE LOGITS
     sessionFactory
    0.30
    asy
    0.29
    .boost
    0.28
    chein
    0.27
    sein
    0.26
    soon
    0.26
    ASY
    0.26
    asia
    0.25
    ginas
    0.24
     gears
    0.23
    Activations Density 0.002%

    No Known Activations