© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58067
    Prev
    Next
    INDEX
    Explanations

    industrial or manufacturing processes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     beg
    -0.29
    tab
    -0.27
     Pent
    -0.27
    å¼¥
    -0.25
    cat
    -0.25
    iddles
    -0.25
     cat
    -0.24
    å®ŀè·µç»ıéªĮ
    -0.24
    azar
    -0.24
    åĪĨæľŁ
    -0.24
    POSITIVE LOGITS
    oire
    0.30
    èĢIJ
    0.28
    -last
    0.28
    moire
    0.27
     fixtures
    0.26
    ç¥ĸåĽ½
    0.26
     Fixture
    0.26
    atypes
    0.26
    æİ©
    0.25
     flushed
    0.25
    Activations Density 0.007%

    No Known Activations