© 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. 48421
    Prev
    Next
    INDEX
    Explanations

    integrals with $x$ and $i$

    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
     ìĿ¸ìłķ
    -0.07
    vet
    -0.07
    å±İ
    -0.06
    elp
    -0.06
     Individual
    -0.06
    åijĬ
    -0.06
    éĴ³
    -0.06
     Pur
    -0.06
    é¼ĵæİĮ
    -0.06
    æݧèĤ¡æľīéĻIJåħ¬åı¸
    -0.06
    POSITIVE LOGITS
    èļĮ
    0.09
    丽ä¸Ŀ
    0.08
    ItemCount
    0.07
     helic
    0.07
    hawk
    0.07
    گذارÛĮ
    0.07
    heu
    0.07
    uctive
    0.07
    åĽŀæĹĭ
    0.07
    dfd
    0.07
    Activations Density 0.004%

    No Known Activations