© 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. 60902
    Prev
    Next
    INDEX
    Explanations

    positions within grids or lists

    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
    åİĨç¨ĭ
    -0.08
    ết
    -0.08
    åľºå¤ĸ
    -0.08
    身ä¸ĸ
    -0.07
    è£ħåľ¨
    -0.07
     portfolios
    -0.07
     markets
    -0.07
    nock
    -0.07
    _BIG
    -0.07
     Kost
    -0.07
    POSITIVE LOGITS
    å±Ĥé«ĺ
    0.08
    å±ĤçļĦ
    0.08
    å±Ĥ
    0.08
     adjacent
    0.08
    ç´§éĤ»
    0.07
    åħ«ä¹Ŀ
    0.07
    缸éĤ»
    0.07
    纵
    0.07
    horizontal
    0.07
    ä¸Ĭä¸Ģå±Ĥ
    0.07
    Activations Density 0.007%

    No Known Activations