© 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. 65459
    Prev
    Next
    INDEX
    Explanations

    tokens like Ga, QA, Jon, fcc

    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
    Ø·ÙĨ
    -0.07
    наÑĩе
    -0.06
    好ä¸į容æĺĵ
    -0.06
     اÙĦØ°Ùĩب
    -0.06
     "~/
    -0.06
     "__
    -0.06
    oar
    -0.06
    æĹ
    -0.06
    ãĤĦãģĭ
    -0.06
    Defs
    -0.06
    POSITIVE LOGITS
    å·´åħĭ
    0.07
     Ofer
    0.07
    _deleted
    0.07
    åĬ±
    0.07
     Ejem
    0.07
    aków
    0.07
    .apps
    0.07
    å¹³æ¹ĸ
    0.07
    ä¹ĭåĽ½
    0.07
     Zob
    0.07
    Activations Density 0.082%

    No Known Activations