© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30953
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    æĹ·
    -0.08
    æĿī
    -0.08
    çĿ¦
    -0.07
     executions
    -0.07
    鸳
    -0.07
    æīĢéķ¿
    -0.07
    سÙĦÙħ
    -0.07
    æī§è¡ĮåĬĽ
    -0.07
    ä½łæĪij
    -0.07
    æĿijæĿij
    -0.07
    POSITIVE LOGITS
     Heller
    0.08
    moz
    0.07
    COUNT
    0.07
    ernet
    0.06
    éĤ£äºĽ
    0.06
    owler
    0.06
    å¼Ģ头çļĦ
    0.06
    çī¹è®Ń
    0.06
    大åݦ
    0.06
    رÙĪÙĬ
    0.06
    Activations Density 0.001%

    No Known Activations