© 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. 3558
    Prev
    Next
    INDEX
    Explanations

    mathematical questions

    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
    анда
    -0.09
    urna
    -0.08
    ÑģÑĤÑĢÑĥ
    -0.08
    çĵ¦å°Ķ
    -0.08
    noop
    -0.08
    ×ķ׾×Ļ×Ŀ
    -0.08
    çĴ¨
    -0.08
    imana
    -0.08
    ouro
    -0.07
    ä¿±è¿Ľ
    -0.07
    POSITIVE LOGITS
    ose
    0.08
    ful
    0.07
    æľī两
    0.06
     Uns
    0.06
    è·ĭ
    0.06
    adh
    0.06
    ighed
    0.06
    unctuation
    0.06
    Uns
    0.06
    ä¹ī
    0.06
    Activations Density 0.004%

    No Known Activations