© 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. 63869
    Prev
    Next
    INDEX
    Explanations

    5 year survival statistics

    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
    -0.06
    ùa
    -0.06
    (Process
    -0.06
    ä¸ŃéĢļ
    -0.06
    rano
    -0.06
    jen
    -0.06
    Pool
    -0.06
    нолог
    -0.06
    .tell
    -0.06
     опÑĤи
    -0.06
    POSITIVE LOGITS
    èĮ«
    0.09
    éĢļè¿ĩè¿ĻäºĽ
    0.08
     estimated
    0.08
     probability
    0.08
    icht
    0.08
     probable
    0.07
     extrapol
    0.07
    Åijs
    0.07
    æĪĸ以ä¸Ĭ
    0.07
     Probability
    0.07
    Activations Density 0.024%

    No Known Activations