© 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. 61830
    Prev
    Next
    INDEX
    Explanations

    plus sign or programming keywords

    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
    indra
    -0.07
    oner
    -0.07
    骨çģ°
    -0.07
    ä¸įä¹ħçļĦå°ĨæĿ¥
    -0.07
    纳æĸ¯
    -0.07
    èĻ
    -0.06
    cab
    -0.06
    cob
    -0.06
    _DONE
    -0.06
    æĹłçĸij
    -0.06
    POSITIVE LOGITS
    åİŁæľī
    0.09
     плÑİÑģ
    0.08
     plus
    0.08
    åİŁæľīçļĦ
    0.07
     original
    0.07
    被éĢ¼
    0.07
    åİŁæľ¬
    0.07
    éŁ
    0.07
    åŁºç¡Ģä¸Ĭ
    0.07
    pragma
    0.07
    Activations Density 0.006%

    No Known Activations