© 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. 40322
    Prev
    Next
    INDEX
    Explanations

    multiple aspects or types

    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
    eves
    -0.07
    .cn
    -0.07
    æĻĴ
    -0.07
     Sem
    -0.06
    ios
    -0.06
    eters
    -0.06
    åIJĪ
    -0.06
     br
    -0.06
    ét
    -0.06
     Pog
    -0.06
    POSITIVE LOGITS
    raga
    0.07
    +)\
    0.07
    æĺ¯ä»Ģä¹Īåij¢
    0.07
     **:**
    0.07
    ½Ķ
    0.07
    çķij
    0.07
    readystatechange
    0.07
    nitt
    0.07
    åĴĮç»´çĶŁç´ł
    0.07
     superiority
    0.07
    Activations Density 0.112%

    No Known Activations