© 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. 8268
    Prev
    Next
    INDEX
    Explanations

    observer dependent quantities

    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
    mania
    -0.08
     PRESID
    -0.08
    被æµıè§Ī
    -0.07
    æİĸ
    -0.07
    è®©æĽ´å¤ļ读èĢħ
    -0.07
    注éĶĢå¤ĩæ¡Ī
    -0.07
    ovens
    -0.07
    被æīĵ
    -0.07
    aries
    -0.07
    æī¾åĩĨ
    -0.07
    POSITIVE LOGITS
     who
    0.09
    çľ¼ä¸ŃçļĦ
    0.08
     seeing
    0.07
    è§Ĵ度çľĭ
    0.07
    çľĭåĪ°çļĦæĺ¯
    0.07
     stationed
    0.07
     viewing
    0.06
    æĸ°å¹´å¿«ä¹IJ
    0.06
     sees
    0.06
    çľĭåĪ°
    0.06
    Activations Density 0.009%

    No Known Activations