© 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. 30680
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

    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
    -script
    -0.07
    æĤ£ä¸Ĭ
    -0.07
    okit
    -0.07
    å¯Ĵé£İ
    -0.07
    éŃĶå¹»
    -0.07
    तà¥įया
    -0.06
    èĤĿçĤİ
    -0.06
    indust
    -0.06
    _stylesheet
    -0.06
    ä¸Ģè¶Ł
    -0.06
    POSITIVE LOGITS
    éĿĻæĢģ
    0.08
    imini
    0.08
    æŀĦéĢł
    0.07
    _listen
    0.07
    лÑĸй
    0.06
    ä¹Ŀæ±Ł
    0.06
    nox
    0.06
    èģĨ
    0.06
    ÑĦина
    0.06
    åĽ½åĨħå¸Ĥåľº
    0.06
    Activations Density 0.318%

    No Known Activations