© 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. 51229
    Prev
    Next
    INDEX
    Explanations

    feedback on

    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
    ities
    -0.08
    ainer
    -0.08
    ishing
    -0.07
    äg
    -0.07
    berger
    -0.07
     debut
    -0.07
    ertz
    -0.07
    íıIJ
    -0.06
    uments
    -0.06
    è¯ºåŁº
    -0.06
    POSITIVE LOGITS
    ات
    0.09
    ש×ķ
    0.08
    ed
    0.08
    åĽŀæĿ¥çļĦ
    0.08
    å°Ķæĸ¯
    0.08
     оÑĢганизма
    0.08
    ÑĢеменно
    0.07
    stuk
    0.07
    æľºåĪ¶
    0.07
    lÄħ
    0.07
    Activations Density 0.028%

    No Known Activations