© 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. 26655
    Prev
    Next
    INDEX
    Explanations

    geographical areas and subdivisions

    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
    اج
    -0.06
    ody
    -0.06
    åģ¶å°Ķ
    -0.06
    çĪ±æĬ¤
    -0.06
    è¦ģå°ıå¿ĥ
    -0.06
    kst
    -0.06
     corporal
    -0.06
    ä¿Ŀåħ»
    -0.06
    åħ¬åħ±åľºæīĢ
    -0.06
    lak
    -0.06
    POSITIVE LOGITS
    带åĬ¨ä½ľçĶ¨
    0.10
    带åĬ¨
    0.10
    ä¸ĸçķĮ级
    0.10
    æĭ³å¤´
    0.09
    åģļ强
    0.09
    åıijå±ķä¸Ń
    0.09
    æ½ľåĬĽ
    0.09
    éĽĨèģļ
    0.09
    è§ĦåĪĴçļĦ
    0.09
    çļĦæĪĺçķ¥
    0.09
    Activations Density 0.101%

    No Known Activations