© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    efficiency, exceeding, flexibility

    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
     Dél
    -0.07
    ä¸įç®Ģåįķ
    -0.07
     entities
    -0.07
    تÙĩÙħا
    -0.07
    squ
    -0.07
    åħ·æľīçĭ¬ç«ĭ
    -0.07
    rawer
    -0.06
    AsStream
    -0.06
    åħ¶ä¸ī
    -0.06
    entities
    -0.06
    POSITIVE LOGITS
    ä¸Ģ缴ä¿ĿæĮģ
    0.09
    ä½İäºİ
    0.09
    VERSE
    0.08
    è¶ĬæĹ©
    0.08
    æĽ²
    0.08
    åĪļ好
    0.08
    ä¸Ģ缴
    0.08
     exceeding
    0.08
     excess
    0.08
    ä¸Ģ缴å¤Ħäºİ
    0.08
    Activations Density 0.016%

    No Known Activations