© 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. 63337
    Prev
    Next
    INDEX
    Explanations

    localized disorder

    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
    çķħ
    -0.09
     busy
    -0.07
    éĩı
    -0.07
    busy
    -0.07
    ä¸Ģè¨Ģ
    -0.07
    _linked
    -0.07
    Å¡ek
    -0.07
    glas
    -0.06
    ä¸į顺
    -0.06
    عب
    -0.06
    POSITIVE LOGITS
     existence
    0.09
    ä¸įæķ£
    0.09
    æłĸ
    0.08
    æĿŁç¼ļ
    0.08
    åŃĺåľ¨
    0.08
    existence
    0.08
    çī¢åĽº
    0.08
    縼
    0.08
    _keeper
    0.08
    exists
    0.08
    Activations Density 0.004%

    No Known Activations