© 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. 20742
    Prev
    Next
    INDEX
    Explanations

    I am missing or doing something 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
    ResponseBody
    -0.09
    ork
    -0.08
    åĨī
    -0.07
     proceeding
    -0.07
     doubtful
    -0.07
     reportedly
    -0.07
    anel
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    çļĦåı¯èĥ½æĢ§
    -0.07
    çļĦç¡®
    -0.07
    POSITIVE LOGITS
    éĶĻäºĨ
    0.09
    éĶĻ
    0.08
     wrong
    0.07
    _wrong
    0.07
    太å¤ļ
    0.07
    éĮ¯
    0.07
     missed
    0.07
    误解
    0.07
    忽çķ¥äºĨ
    0.07
    æĪij太
    0.07
    Activations Density 0.039%

    No Known Activations