© 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. 9051
    Prev
    Next
    INDEX
    Explanations

    geographical administrative divisions

    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
    undle
    -0.07
    respect
    -0.07
    çĬ¯çļĦ
    -0.07
    åIJĪä½ĵ
    -0.07
    astian
    -0.07
    åIJį为
    -0.06
     foul
    -0.06
    ä¸į欲
    -0.06
    otos
    -0.06
    æŀĹçļĦ
    -0.06
    POSITIVE LOGITS
     appunto
    0.07
    வà¯Ī
    0.07
    âĢİ
    0.07
     Patrimonio
    0.07
    ä¸ĩå¹´
    0.07
    羨
    0.06
    ħ
    0.06
    ért
    0.06
    åĵªå®¶å¥½
    0.06
    帮åĬ©ä¸Ńå¿ĥ
    0.06
    Activations Density 0.290%

    No Known Activations