© 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. 13701
    Prev
    Next
    INDEX
    Explanations

    Aharonov-Casher, Aharonov-Bohm, winding numbers

    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
     رØŃÙħ
    -0.08
    å§Ĺ
    -0.07
    andes
    -0.07
    çĸıæĿ¾
    -0.07
    à¸Ľà¸£à¸°à¸Ĭ
    -0.07
     waste
    -0.06
    ÑģÑĤави
    -0.06
    .dense
    -0.06
     Swal
    -0.06
    _recursive
    -0.06
    POSITIVE LOGITS
    ç»ķè¡Į
    0.08
    æį»
    0.08
    åĽŀæĿ¥åIJİ
    0.08
     threading
    0.07
    ä¸ĢåľĪ
    0.07
     completeness
    0.07
    ZI
    0.07
    ç»ķ
    0.07
    _INC
    0.07
    ä¸įèĥ½å®Įåħ¨
    0.07
    Activations Density 0.009%

    No Known Activations