© 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. 15030
    Prev
    Next
    INDEX
    Explanations

    what is wrong

    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
    /maps
    -0.09
    ä¸ĩäºĭ
    -0.08
    ansom
    -0.08
    endorf
    -0.07
    符åIJĪæĿ¡ä»¶
    -0.07
    ellular
    -0.07
    èĢ³çĽ®
    -0.07
    å¾Ĺä¸Ĭ
    -0.07
    äºĭåıĺ
    -0.07
     ìķĪìłķ
    -0.07
    POSITIVE LOGITS
    åĴĮä¸į足
    0.13
    ä¹ĭå¤Ħ
    0.11
    严éĩįçļĦ
    0.08
    æīĢåľ¨
    0.08
    主è¦ģ表çİ°åľ¨
    0.08
    åľ¨äºİ
    0.08
    ä¸įæĩĤå¾Ĺ
    0.08
    主è¦ģä½ĵçİ°åľ¨
    0.08
    ä¹ĭèĻķ
    0.08
    ä¹ĭå¤Ħåľ¨äºİ
    0.08
    Activations Density 0.115%

    No Known Activations