© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    necessary and sufficient conditions

    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
     Quay
    -0.08
    hra
    -0.08
    é¤ĺ
    -0.08
    æľīä½Ļ
    -0.08
    عط
    -0.08
    άλιÏĥÏĦα
    -0.07
    ç¥Ŀç¦ıä½ł
    -0.07
    ãģ«ãģĤãģŁ
    -0.07
    _namespace
    -0.07
    è¿ĻæĬĬ
    -0.07
    POSITIVE LOGITS
    å¿ħé¡»æľī
    0.12
    å¿ħé¡»è¦ģæľī
    0.11
    ä¸Ģå®ļè¦ģæľī
    0.11
    å¿ħå®ļ
    0.10
    Must
    0.10
     must
    0.10
    å¿ħé¡»åħ·å¤ĩ
    0.10
    ä¹Łå¿ħé¡»
    0.10
     Must
    0.09
    must
    0.09
    Activations Density 0.026%

    No Known Activations