© 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. 30-TRANSCODER-HP
    7. 95703
    Prev
    Next
    INDEX
    Explanations

    Money transfers and transactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exchange
    -0.28
     Exchange
    -0.28
    ãĥ¼ãĤ·ãĥ§ãĥ³
    -0.27
     Morg
    -0.26
    aut
    -0.26
     convin
    -0.26
    jective
    -0.26
    交æµģ
    -0.26
     sust
    -0.25
    uchos
    -0.25
    POSITIVE LOGITS
    追踪
    0.29
    è¾ĥå°ı
    0.28
    Scheduled
    0.28
     INST
    0.27
     schedule
    0.27
    ìķĪëĤ´
    0.26
    _inline
    0.26
     scheduling
    0.26
    trimmed
    0.26
    scheduled
    0.26
    Activations Density 0.886%

    No Known Activations