© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17940
    Prev
    Next
    INDEX
    Explanations

    special characters or math notation

    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
    CIL
    -0.07
    åı¸
    -0.06
     room
    -0.06
     warmed
    -0.06
    贯彻æī§è¡Į
    -0.06
    转载请注æĺİ
    -0.06
     average
    -0.06
    åħ¨å¿ĥ
    -0.06
    çĽ
    -0.06
    æł¸
    -0.06
    POSITIVE LOGITS
    æĭīéĩĮ
    0.09
    iefert
    0.09
    uris
    0.08
    LEC
    0.08
    ä¸Ģåľ°
    0.08
     Tám
    0.08
    èIJ¨æĸ¯
    0.08
    æĶ¿æ²»å±Ģ
    0.08
    лев
    0.08
    ublic
    0.07
    Activations Density 0.002%

    No Known Activations