© 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. 22710
    Prev
    Next
    INDEX
    Explanations

    calculation and math problems

    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
     Punya
    -0.08
    holt
    -0.08
    erat
    -0.08
    conj
    -0.07
    تز
    -0.07
    ç´«èįĨ
    -0.07
    è¿ĺæľīä¸įå°ij
    -0.07
    ric
    -0.07
    æĶ¯ä¹¦
    -0.07
     Alm
    -0.07
    POSITIVE LOGITS
    åįĴ
    0.07
    -comp
    0.07
    补足
    0.07
    ableObject
    0.07
    unden
    0.06
    èªĵ
    0.06
    itchen
    0.06
     comprom
    0.06
    raig
    0.06
    ç«Ń
    0.06
    Activations Density 0.003%

    No Known Activations