© 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. 50844
    Prev
    Next
    INDEX
    Explanations

    rounding numbers to specific decimal places

    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
    å¿Ļ
    -0.08
    å¿ĻçļĦ
    -0.07
    صرÙĬØ©
    -0.07
    åĻ¨æ¢°
    -0.07
    ç¯Ħ
    -0.07
    ezz
    -0.06
    its
    -0.06
    ange
    -0.06
    inky
    -0.06
    æĪijçļĦç¥Ŀç¦ı
    -0.06
    POSITIVE LOGITS
    ertainment
    0.07
    }${
    0.07
    éĻĨ
    0.07
    ydd
    0.07
    æ°¸åĴĮ
    0.06
    borg
    0.06
    娱
    0.06
    ACH
    0.06
    aches
    0.06
    indu
    0.06
    Activations Density 0.014%

    No Known Activations