© 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. 42359
    Prev
    Next
    INDEX
    Explanations

    SVG path data

    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
     Newman
    -0.08
    丼çĶŁ
    -0.07
    ach
    -0.07
    eldet
    -0.07
    λÏİ
    -0.07
    è¿ĺåĸľæ¬¢
    -0.07
    çĽijäºĭ
    -0.07
     doss
    -0.07
    Õ¡Õ¯Õ¡Õ¶
    -0.07
    ļĮ
    -0.06
    POSITIVE LOGITS
    æŁĵ
    0.08
    åī²
    0.07
    åį
    0.07
    çĻ½æ²Ļ
    0.07
    å®°
    0.06
    å°ģ
    0.06
    .getRuntime
    0.06
    ä¿ĬæĿ°
    0.06
    odzi
    0.06
    åģĩ
    0.06
    Activations Density 0.001%

    No Known Activations