© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    aina
    -0.07
    è¿Ľè¡Į交æĺĵ
    -0.07
    æĺ¯åħ·æľī
    -0.07
     sogenannten
    -0.06
    _names
    -0.06
    åħ·æľī以ä¸ĭ
    -0.06
    飬
    -0.06
    è¿Ľè¡ĮåŃ¦ä¹ł
    -0.06
    ä¾ĽåºĶ产åĵģ
    -0.06
    å°¤åħ¶æĺ¯
    -0.06
    POSITIVE LOGITS
     tadi
    0.09
     kia
    0.08
    hlen
    0.07
    baran
    0.07
    两ä¸į误
    0.07
    å¦Ĥçİī
    0.07
     dll
    0.07
    spot
    0.07
    éĢĹ
    0.07
    èĥ½è®©
    0.07
    Activations Density 0.006%

    No Known Activations