© 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. 12672
    Prev
    Next
    INDEX
    Explanations

    computer algebra, fiddle link, confirm

    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
    çīµ
    -0.08
    eries
    -0.07
    akit
    -0.07
    epar
    -0.07
    ç»Ĩç»Ĩ
    -0.07
     Trik
    -0.07
    çĥ¦
    -0.07
    æī¯
    -0.07
     explicou
    -0.07
    ç¹ģ
    -0.07
    POSITIVE LOGITS
    ä¸İ伦
    0.08
    è¯ģå®ŀ
    0.07
    .run
    0.07
     confirme
    0.07
    è·ijäºĨ
    0.07
    èįī
    0.07
    alth
    0.06
    bert
    0.06
     confirm
    0.06
    ÙĨدر
    0.06
    Activations Density 0.039%

    No Known Activations