© 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. 9323
    Prev
    Next
    INDEX
    Explanations

    Russian Federation

    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
    篱
    -0.07
    ç¬ĭ
    -0.07
     binary
    -0.06
    éĽķ
    -0.06
    éĺ¶
    -0.06
    ÑģÑĤÑĮÑİ
    -0.06
     disruptive
    -0.06
    认
    -0.06
    lash
    -0.06
    åįĬå±±
    -0.06
    POSITIVE LOGITS
    è©IJ
    0.08
    handlers
    0.08
    à¸Ľà¸£à¸°à¸Īำวัà¸Ļ
    0.08
    ë¬ĺ
    0.08
    æ¯Ķè¾ĥå¤įæĿĤ
    0.07
    ivil
    0.07
    大å®Ŀ
    0.07
    adiator
    0.07
    çŃĭèĤī
    0.07
    stuff
    0.07
    Activations Density 0.002%

    No Known Activations