© 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. 60141
    Prev
    Next
    INDEX
    Explanations

    in the case of

    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
     hence
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
    è¿Ļæĺ¯ä¸ª
    -0.07
    è¿Ļæ³¢
    -0.07
     now
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    è¿Ļä¸Ģå¹ķ
    -0.07
     hiervoor
    -0.07
    è¿Ļä¸ĢåĪ»
    -0.07
    TTY
    -0.07
    POSITIVE LOGITS
    ãģĺãĤģãģ¦
    0.10
    ä¸įä½Ĩ
    0.09
    upon
    0.08
    ä¹Łæĺ¯æľĢ
    0.08
    ä¸įä»ħæľī
    0.08
    çļĦéĹ®é¢ĺæĺ¯
    0.08
    ìĹIJëıĦ
    0.08
    ä¸įä»ħèĥ½å¤Ł
    0.08
    ä¸įä»ħ
    0.08
     nejen
    0.08
    Activations Density 0.049%

    No Known Activations