© 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. 17610
    Prev
    Next
    INDEX
    Explanations

    mathematical product notation

    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
    eres
    -0.08
    Õ§
    -0.07
    ered
    -0.07
    erer
    -0.07
    er
    -0.07
    icismo
    -0.06
    çĶ¨ä¹¦
    -0.06
    ä¸İæĻ®éĢļ
    -0.06
    arin
    -0.06
    spflicht
    -0.06
    POSITIVE LOGITS
    Ø©
    0.08
    oms
    0.08
    omial
    0.08
    logue
    0.08
    æĹłéĹ´
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.07
    ampoline
    0.07
    ä¸įçł´
    0.07
    æ¹ĸåĮº
    0.07
    ervers
    0.07
    Activations Density 0.004%

    No Known Activations