© 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. 20076
    Prev
    Next
    INDEX
    Explanations

    programming expressions

    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
    efon
    -0.06
    æĺ¯æĹ¥æľ¬
    -0.06
    anel
    -0.06
    计ç®ĹçļĦ
    -0.06
     unrelated
    -0.06
    ãģ¼ãģĨ
    -0.06
    é¢ĸ
    -0.06
    essin
    -0.06
     Silence
    -0.06
    ánt
    -0.06
    POSITIVE LOGITS
    ahi
    0.08
     Thesis
    0.07
    ernals
    0.07
    ahari
    0.07
    rts
    0.07
    à¹Ģà¸ģล
    0.07
    SharedPtr
    0.07
    å¾ĹæĿ¥
    0.07
    _goto
    0.06
    hari
    0.06
    Activations Density 0.002%

    No Known Activations