© 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. 44002
    Prev
    Next
    INDEX
    Explanations

    foreigners locals natives

    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
    åģļ人
    -0.07
    ä¸Ģ次åıĪä¸Ģ次
    -0.06
    vain
    -0.06
    æľ¬æĿ¥æĺ¯
    -0.06
    æĭĽåķĨåĬłçĽŁ
    -0.06
    æľĢç»Ī
    -0.06
     rightfully
    -0.06
     ultimately
    -0.06
    åĴ¬çīĻåĪĩ
    -0.06
    è¶Ĭæĥ³
    -0.06
    POSITIVE LOGITS
    å½ĵåľ°äºº
    0.10
    è¯¥åĽ½
    0.10
     foreigners
    0.09
    locals
    0.09
    æ¦ĤåĨµ
    0.09
     locals
    0.08
     natives
    0.08
    è·¯éĢı
    0.08
    åĴĮä¸ŃåĽ½
    0.08
    _translate
    0.08
    Activations Density 0.197%

    No Known Activations