© 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. 21982
    Prev
    Next
    INDEX
    Explanations

    places or structures

    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
    è¿Ľ
    -0.07
    ä»İä¸ŃåĽ½
    -0.07
    ühr
    -0.06
    èĢħåı¯
    -0.06
     reversal
    -0.06
     plus
    -0.06
    _again
    -0.06
    kte
    -0.06
    çĮ®ä¸Ĭ
    -0.06
    à¸Ĭี
    -0.06
    POSITIVE LOGITS
     confines
    0.08
    ffin
    0.08
    é£İéĻ©çĽijæݧ
    0.08
    store
    0.08
    æº
    0.08
    à¸ļาล
    0.07
    iany
    0.07
    æĿŁç¼ļ
    0.07
    สูà¹Ī
    0.07
    antro
    0.07
    Activations Density 0.207%

    No Known Activations