© 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. 56397
    Prev
    Next
    INDEX
    Explanations

    cantelope

    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
    Ïģκ
    -0.07
    ÙĪظ
    -0.07
    icer
    -0.07
    urf
    -0.07
    åĴ¬çīĻ
    -0.07
    æľĿ天
    -0.07
    åĽłèĢĮ
    -0.06
     Hybrid
    -0.06
     därför
    -0.06
    Defaults
    -0.06
    POSITIVE LOGITS
    ä½ķåħ¶
    0.08
    ä¼¼ä¹İ
    0.08
    ä¸į对
    0.07
    è¿Ļä¹Īç®Ģåįķ
    0.07
    _refs
    0.07
    ç«ŁçĦ¶
    0.07
     NGH
    0.07
     Borsa
    0.07
    ä¿Ŀå®ī
    0.07
    çľĭä¼¼
    0.07
    Activations Density 0.002%

    No Known Activations