© 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. 31-TRANSCODER-HP
    7. 18787
    Prev
    Next
    INDEX
    Explanations

    Disease outbreaks and cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīģ
    -0.28
    主页
    -0.28
    åĮ¾
    -0.27
    Bracket
    -0.26
    ÑĪка
    -0.25
    trä
    -0.24
     univers
    -0.24
    æĹ¥è®¯
    -0.23
    æ¯ķä¸ļ
    -0.23
    ниÑĨÑĭ
    -0.23
    POSITIVE LOGITS
     human
    0.34
    cases
    0.32
     known
    0.32
    _known
    0.31
    known
    0.31
     cases
    0.30
    Cases
    0.29
    lover
    0.27
     case
    0.26
    iller
    0.26
    Activations Density 0.906%

    No Known Activations