© 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. 17787
    Prev
    Next
    INDEX
    Explanations

    subscripts and superscripts

    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
    æ®Ĩ
    -0.08
    sworth
    -0.08
    fras
    -0.08
    çŃ
    -0.08
    rasing
    -0.08
    ÃīM
    -0.07
    amba
    -0.07
    worth
    -0.07
    باب
    -0.07
    ủa
    -0.07
    POSITIVE LOGITS
    arki
    0.07
    ç«ĭåį³ä¸ĭè½½
    0.07
    âĢ¦and
    0.07
     Yourself
    0.07
    ÙĨÙĬÙģ
    0.06
    yt
    0.06
     ence
    0.06
    âĢ¦but
    0.06
     préfér
    0.06
     hott
    0.06
    Activations Density 0.013%

    No Known Activations