© 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. 32111
    Prev
    Next
    INDEX
    Explanations

    development, evolution, violation

    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
    reta
    -0.07
    ä¸ŃåĽ½ç½ij
    -0.07
    åĨĴåħħ
    -0.07
     again
    -0.07
    reira
    -0.07
    æ¶īåıĬ
    -0.07
     evidently
    -0.07
    asen
    -0.06
    Operation
    -0.06
    ivan
    -0.06
    POSITIVE LOGITS
    ห
    0.07
    ä¸ĭä¸Ģç§Ĵ
    0.07
    å·®ä¸įå¤ļ
    0.07
     suivantes
    0.06
    éģµå®ĪåĽ½å®¶
    0.06
    åı¦ä¸Ģ
    0.06
    ä¹Łæĺ¯æĪij们
    0.06
    ãģĿãģĨãģ§
    0.06
    禧
    0.06
     Feu
    0.06
    Activations Density 0.197%

    No Known Activations