© 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. 45644
    Prev
    Next
    INDEX
    Explanations

    surface, superficial, veneer, guise, rhetoric

    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
    اث
    -0.07
     باÙĦض
    -0.07
    æ½ľ
    -0.07
    ä¸ŃåĽ½å®¶
    -0.07
    å¿Ĩ
    -0.07
    ellate
    -0.07
    åľ°éģĵ
    -0.07
    æģ°
    -0.07
    çĸ¯äºĨ
    -0.07
    éĩĪ
    -0.07
    POSITIVE LOGITS
    表éĿ¢
    0.13
    表象
    0.11
     superficial
    0.11
    çļĦ表éĿ¢
    0.11
     surface
    0.11
    表éĿ¢çļĦ
    0.10
    表éĿ¢ä¸Ĭ
    0.10
    表å±Ĥ
    0.09
    surface
    0.09
    ä¸İå®ŀéĻħ
    0.09
    Activations Density 0.055%

    No Known Activations