© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61870
    Prev
    Next
    INDEX
    Explanations

    date or number separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     V
    -0.08
     loc
    -0.07
     Seg
    -0.07
    V
    -0.06
    ä¸ĩå²ģ
    -0.06
    .nih
    -0.06
     segments
    -0.06
     sets
    -0.06
    -0.06
     entities
    -0.06
    POSITIVE LOGITS
     serialVersionUID
    0.09
    enheim
    0.09
    fila
    0.09
    æľĪçĶŁ
    0.08
    æĹ¥çĶŁ
    0.08
    pmat
    0.08
    uvi
    0.08
    ldata
    0.08
    LinkId
    0.08
    ÃĶNG
    0.08
    Activations Density 0.006%

    No Known Activations