© 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. 49232
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
     (“
    -0.08
    ’n
    -0.07
    åIJİèĢħ
    -0.07
    ç¼ĸæİĴ
    -0.07
    ’:
    -0.07
     presently
    -0.07
    lamp
    -0.07
    ÑĢеÑĨ
    -0.07
    allah
    -0.07
    æľĹ
    -0.06
    POSITIVE LOGITS
    åħ¶ä»ĸçļĦ
    0.08
    .WriteString
    0.08
    æĪijèĩªå·±
    0.07
    åı¯èĥ½ä¼ļæľī
    0.07
    consider
    0.07
    ç®Ĺæĺ¯
    0.07
    æ¯ĶæĪij
    0.07
    ä¸Ģå®ļä¼ļ
    0.07
    æĻ®æ³ķ
    0.07
    æĪijä¸Ģ个人
    0.07
    Activations Density 0.014%

    No Known Activations