© 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. 43589
    Prev
    Next
    INDEX
    Explanations

    screen contact fire typically fits

    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
    chan
    -0.07
    ä¸ĬéĿ¢
    -0.07
    大æ¦Ĥæĺ¯
    -0.07
    åĽłä¸ºæľī
    -0.07
    å¹²ä»Ģä¹Ī
    -0.07
    гава
    -0.07
    æIJŀ
    -0.07
    yi
    -0.06
    åĽłä¸º
    -0.06
    بس
    -0.06
    POSITIVE LOGITS
    以ä¸ĭãģ®
    0.08
    æķħéĢī
    0.07
    ä¸ĭè¿°
    0.07
    åĪĩå®ŀç»´æĬ¤
    0.07
    éĢģèĩ³
    0.07
    ä¸ĭè¨ĺãģ®
    0.07
     pertanto
    0.07
    åŃ°
    0.07
     balk
    0.07
    âĨĵâĨĵ
    0.06
    Activations Density 0.001%

    No Known Activations