© 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. 42468
    Prev
    Next
    INDEX
    Explanations

    pressure and PSI

    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
    æ£ĭåŃIJ
    -0.08
    饿
    -0.07
    æİłå¤º
    -0.07
    éĿ¢ç§¯è¾¾
    -0.07
    éĿ¢ç§¯ä¸º
    -0.06
    ÑıзÑĭ
    -0.06
    izio
    -0.06
    éĿ¢ç§¯çļĦ
    -0.06
    èĢĥæĭī
    -0.06
    ilas
    -0.06
    POSITIVE LOGITS
     pressure
    0.14
    åİĭåĬĽ
    0.14
    åİĭåĬĽçļĦ
    0.13
    -pressure
    0.13
     pressures
    0.13
    pressure
    0.12
     Pressure
    0.12
    åİĭåĬĽä¸ĭ
    0.12
    åİĭåĬĽåĴĮ
    0.11
    çļĦåİĭåĬĽ
    0.11
    Activations Density 0.046%

    No Known Activations