© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11814
    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
    ynth
    -0.08
    æľªå©ļ
    -0.08
    önt
    -0.08
    æĪ·
    -0.08
    _diff
    -0.08
    é¦ĸæĴŃ
    -0.07
    éĩįåĨĻ
    -0.07
     ugy
    -0.07
    çªľ
    -0.07
    itage
    -0.07
    POSITIVE LOGITS
    ä¸įåħħåĪĨ
    0.08
    åħ³ç³»
    0.07
    åħ³ç³»ä¸Ń
    0.07
    Ùħبر
    0.06
     causal
    0.06
     Rhodes
    0.06
    éĿŀå¿ħè¦ģ
    0.06
     relations
    0.06
    cca
    0.06
    ç©·
    0.06
    Activations Density 0.001%

    No Known Activations