© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21941
    Prev
    Next
    INDEX
    Explanations

    a bit of good news

    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
    èģĶå¸Ń
    -0.08
    åĨ³
    -0.08
    æĽ´åĸľæ¬¢
    -0.07
    为äºĨæĽ´å¥½çļĦ
    -0.07
    visions
    -0.07
    强强
    -0.07
    luv
    -0.07
    olto
    -0.07
    å°½èĩªå·±
    -0.06
    oplan
    -0.06
    POSITIVE LOGITS
    åĶ¯ä¸Ģä¸Ģ个
    0.10
     ìľłìĿ¼
    0.10
    æĥŁæľī
    0.09
    åı¯éĿł
    0.09
    åĶ¯ä¸Ģ
    0.09
     safest
    0.09
    åĶ¯æľī
    0.08
     ìľłìĿ¼íķľ
    0.08
     reliable
    0.08
     reliably
    0.08
    Activations Density 0.039%

    No Known Activations