© 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. 31016
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with 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
    ÑĢÑı
    -0.07
    -refresh
    -0.07
    åīįåIJİçļĦ
    -0.07
    _refresh
    -0.07
    æijĩæijĩ
    -0.07
    è¿Ľåıĸ
    -0.07
    __:
    -0.06
    sur
    -0.06
    常åĬ¡
    -0.06
    åĨħèĨľ
    -0.06
    POSITIVE LOGITS
     ÙĤص
    0.07
    åĪĨ享åĨħ容
    0.07
    asseur
    0.07
    istin
    0.07
    ipa
    0.07
    _sym
    0.07
    eler
    0.07
    arrer
    0.07
    åħ³æ³¨åħ¬ä¼Ĺåı·
    0.07
    éĩį大éĹ®é¢ĺ
    0.07
    Activations Density 0.002%

    No Known Activations