© 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. 9347
    Prev
    Next
    INDEX
    Explanations

    whose

    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
    croft
    -0.07
    aná
    -0.06
    ÏĦίαÏĤ
    -0.06
    åľ°ä¸Ĭ
    -0.06
    èĴĤæĸ¯
    -0.06
    çĩ
    -0.06
    бал
    -0.06
    åħ¢åħ¢
    -0.06
    quel
    -0.06
    ä¼ĹæīĢåij¨çŁ¥
    -0.06
    POSITIVE LOGITS
     whose
    0.11
    whose
    0.09
     cuya
    0.09
     cuyos
    0.08
    riers
    0.08
    ells
    0.08
     cuyo
    0.08
    ä»¬åľ¨
    0.07
    çļĦäººåľ¨
    0.07
    less
    0.07
    Activations Density 0.041%

    No Known Activations