© 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. 61937
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions or sequences

    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
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.08
    weiler
    -0.07
    ád
    -0.07
    èĪİ
    -0.07
    ئÙĩ
    -0.07
    è¶ħè¿ĩ约
    -0.07
    alis
    -0.07
    anlage
    -0.07
    emente
    -0.06
    unta
    -0.06
    POSITIVE LOGITS
    ä¹ħ
    0.07
    åĢĴæķ°
    0.07
    ç¼ĵ
    0.07
    åĢĴåľ¨
    0.07
    æ³Ľ
    0.06
    áĥĶáĥłáĥĹ
    0.06
    raction
    0.06
     Jad
    0.06
    osh
    0.06
     обÑĢаÑĤ
    0.06
    Activations Density 0.006%

    No Known Activations