© 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. 1556
    Prev
    Next
    INDEX
    Explanations

    word or phrase usage

    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
    è¦ģåģļåĪ°
    -0.07
    gak
    -0.07
    æīĢéľĢè¦ģ
    -0.07
    è¿Ļå°±éľĢè¦ģ
    -0.07
    cek
    -0.07
    èµĸ
    -0.07
    è¦ģç»ı常
    -0.07
    è¦ģæľī
    -0.07
    qus
    -0.07
    羣æŃ£åģļåĪ°
    -0.07
    POSITIVE LOGITS
    ç»ĵæŀľæĺ¯
    0.11
     ÑĢезÑĥлÑĮÑĤаÑĤом
    0.10
     resultant
    0.09
    çļĦç»ĵæŀľ
    0.09
    Upon
    0.09
     outcome
    0.09
     result
    0.09
    çļĦè¾ĵåĩº
    0.09
     Upon
    0.09
     resulting
    0.09
    Activations Density 0.098%

    No Known Activations