© 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. 17218
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    éĻIJ度
    -0.06
    大è§Ħ模çļĦ
    -0.06
    建ç«ĭåľ¨
    -0.06
    çİ°å°±
    -0.06
    éķ¿æľŁçļĦ
    -0.06
    大éģĵ
    -0.06
    Ñģл
    -0.06
    orro
    -0.06
     ph
    -0.06
    å°±æĺ¯äºĨ
    -0.05
    POSITIVE LOGITS
    MimeType
    0.08
    æİĴ头
    0.08
    æľ«é¡µ
    0.08
    erÃŃa
    0.08
    INGER
    0.08
    еÑĨ
    0.08
    nger
    0.08
    MISSION
    0.08
    WithValue
    0.07
    åıijå¸ĥèĢħ
    0.07
    Activations Density 0.001%

    No Known Activations