© 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. 21035
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    iah
    -0.07
    以身
    -0.07
    ä¸ĵ
    -0.07
    ixe
    -0.07
    prene
    -0.07
    utile
    -0.07
    jan
    -0.07
    _exc
    -0.07
    laws
    -0.07
    æīģ
    -0.06
    POSITIVE LOGITS
    äºijå³°
    0.07
    移åĭķ
    0.07
    认è¯ĨçļĦ
    0.07
    mene
    0.07
    (--
    0.07
    ä¹ĭä¸ĭçļĦ
    0.07
    ä½µ
    0.07
    æĥ³ä½ł
    0.06
    并éĩį
    0.06
    ä¸įèĭŁ
    0.06
    Activations Density 0.002%

    No Known Activations