© 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. 32-TRANSCODER-HP
    7. 43455
    Prev
    Next
    INDEX
    Explanations

    Software development/code context

    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
    urations
    -0.30
    PREFIX
    -0.26
     INTERRU
    -0.25
    illon
    -0.25
    ÑijÑĢ
    -0.24
     innov
    -0.24
     DISPATCH
    -0.23
    工夫
    -0.23
    ngth
    -0.23
     Innov
    -0.23
    POSITIVE LOGITS
     abs
    0.32
    宿
    0.28
    åĨįåİ»
    0.28
    fan
    0.26
    utan
    0.26
     esp
    0.25
    ระà¸ļ
    0.25
    ắc
    0.25
    åľĪ
    0.25
    -spec
    0.25
    Activations Density 0.002%

    No Known Activations