© 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. 24008
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code snippets

    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±±éķĩ
    -0.07
    fes
    -0.06
    io
    -0.06
    chu
    -0.06
    æŶäºĭ
    -0.06
    ICHE
    -0.06
     Guaranteed
    -0.06
    ILED
    -0.06
    ACE
    -0.06
    fos
    -0.06
    POSITIVE LOGITS
    èĴĤæĸ¯
    0.08
    åłĤ
    0.08
    oczyn
    0.07
    çķĻè¨ĢæĿ¿
    0.07
    æĬĬ人
    0.07
    æķ´
    0.07
    ë¦Ħ
    0.07
    注éĶĢå¤ĩæ¡Ī
    0.07
     Ving
    0.07
    .appendChild
    0.07
    Activations Density 0.001%

    No Known Activations