© 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. 23331
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    iras
    -0.07
    æıIJé«ĺå·¥ä½ľæķĪçİĩ
    -0.07
    rame
    -0.07
    stående
    -0.07
    OLE
    -0.07
    å¿ĥä¸Ĭ
    -0.06
    åģ¶
    -0.06
    utters
    -0.06
    åĪĨéħį
    -0.06
    好èĩªå·±çļĦ
    -0.06
    POSITIVE LOGITS
    éĢĨè¡Į
    0.07
    çĽĸä¸ĸ
    0.07
    äºİä¸ĸ
    0.07
    aktor
    0.06
    spir
    0.06
    vert
    0.06
    лиÑģÑĤÑĭ
    0.06
    Titles
    0.06
    ãģŀ
    0.06
    æģIJæĢĸ
    0.06
    Activations Density 0.002%

    No Known Activations