© 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. 24171
    Prev
    Next
    INDEX
    Explanations

    mathematical continuity and quantification

    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
    èĴĤæĸ¯
    -0.09
    amakan
    -0.09
     dán
    -0.08
    ÑĢома
    -0.08
    icana
    -0.08
    iques
    -0.08
    vestir
    -0.08
    endam
    -0.08
    该èĤ¡
    -0.08
    åĦŁ
    -0.08
    POSITIVE LOGITS
    æĹłéĻIJ
    0.07
     infinite
    0.07
    dy
    0.07
     clos
    0.07
     infinitely
    0.07
    ç²¾å¯Ĩ
    0.06
    .Callback
    0.06
    ç´§æī£
    0.06
    ç²¾
    0.06
    å½ĵ羣
    0.06
    Activations Density 0.016%

    No Known Activations