© 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. 29780
    Prev
    Next
    INDEX
    Explanations

    \:\s*.*,?\s*\w+\s*\:

    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
    éĩijçłĸ
    -0.07
    å°±ç®Ĺ
    -0.07
    urin
    -0.07
    æł¹æľ¬å°±æĺ¯
    -0.07
    bler
    -0.06
    rm
    -0.06
    å¦ĤèĬ±
    -0.06
    toFloat
    -0.06
    tom
    -0.06
    å¸ľ
    -0.06
    POSITIVE LOGITS
     privilegi
    0.07
    ãĢģ
    0.07
    duit
    0.07
    ayet
    0.07
    onsin
    0.07
    ãģĹãģŁãģĵãģ¨
    0.07
    elpers
    0.07
    æĿĪ
    0.07
     comps
    0.06
    ?,?,?,?,
    0.06
    Activations Density 0.031%

    No Known Activations