© 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. 12979
    Prev
    Next
    INDEX
    Explanations

    written in, stream of, existing domain, uploaded files

    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
    æ°´éĩĮ
    -0.07
    æ°ĵ
    -0.07
     ÙĪÙģÙĬ
    -0.06
    æĸ¹ãģĮ
    -0.06
    å©ķ
    -0.06
     ìłķë¶ĢëĬĶ
    -0.06
    é¡įãģ¯
    -0.06
    ForResource
    -0.06
    ForKey
    -0.06
    èµĦæĸĻæĺ¾ç¤º
    -0.06
    POSITIVE LOGITS
     onto
    0.13
     into
    0.12
     kedalam
    0.12
    ))/(
    0.12
    into
    0.11
    çļĦæĸ¹æ³ķæĿ¥
    0.11
    ))/
    0.11
    çĶŁæķĪä¹ĭæĹ¥èµ·
    0.10
    Into
    0.10
     hinzu
    0.10
    Activations Density 1.158%

    No Known Activations