© 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. 64273
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     (âĢ¦)
    -0.07
    Âł
    -0.07
    ent
    -0.07
    f
    -0.07
     âĢ¦
    -0.07
     tr
    -0.07
     relative
    -0.07
    idi
    -0.07
    _optimizer
    -0.06
    ident
    -0.06
    POSITIVE LOGITS
    èıģ
    0.09
    ÙģÙĪر
    0.09
     vær
    0.08
    obat
    0.08
    å·¥ä½ľè¿Ľè¡Į
    0.08
    ä¹ĭå®Ŀ
    0.08
    abinet
    0.08
    ÑĤел
    0.08
    تاب
    0.07
    пеÑĢа
    0.07
    Activations Density 0.005%

    No Known Activations