© 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. 8077
    Prev
    Next
    INDEX
    Explanations

    math, numbers, and code comments

    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
    ane
    -0.07
    æĺ±
    -0.07
    orgen
    -0.06
     Sting
    -0.06
    æĿ¯æ°´
    -0.06
    ani
    -0.06
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.06
    precation
    -0.06
    å·¥åºı
    -0.06
    ä¸įè´Ł
    -0.06
    POSITIVE LOGITS
    éĤ£ä¸Ģå¹´
    0.08
    Occurred
    0.08
    LIKELY
    0.08
    å¿ħçŃĶ
    0.07
    飬
    0.07
    nal
    0.07
    ä¸Ģè´¯
    0.07
     Ao
    0.07
    çݯå¢ĥä¸İ
    0.07
    знÑı
    0.07
    Activations Density 0.014%

    No Known Activations