© 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. 41001
    Prev
    Next
    INDEX
    Explanations

    getting around

    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
    unner
    -0.07
    缸åºĶçļĦ
    -0.07
     consequently
    -0.07
    éĶĻ误æĪĸ
    -0.07
     accordingly
    -0.07
    ernals
    -0.07
    خب
    -0.07
    reff
    -0.06
    ç«ĭäºİ
    -0.06
     hence
    -0.06
    POSITIVE LOGITS
    åĵªæľī
    0.08
    æľ¬èº«å°±
    0.08
    æĭľæīĺ
    0.07
    åĺĽ
    0.07
    åıĤä¸İè¯Ħ论
    0.07
     itself
    0.07
    “He
    0.07
    æľ¬èº«å°±æĺ¯
    0.07
    æľ¬æĿ¥å°±æĺ¯
    0.07
     przecież
    0.07
    Activations Density 0.006%

    No Known Activations