© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    cost vs. benefit evaluation

    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
    epak
    -0.08
    antina
    -0.08
    ë§Įíķľ
    -0.08
    yani
    -0.08
    PACK
    -0.07
    太强
    -0.07
    身æīĭ
    -0.06
    微信æī«ä¸Ģæī«
    -0.06
    TAG
    -0.06
     PACK
    -0.06
    POSITIVE LOGITS
    ä¹ŁæĽ´
    0.09
    éģ¿åħįäºĨ
    0.08
    åĪº
    0.08
    éģ¿åħįåĽł
    0.08
    大大éĻįä½İ
    0.08
    è¿Ļ对äºİ
    0.07
    èıĬ
    0.07
    heim
    0.07
    åĽŀå½Ĵ
    0.07
    æĽ´åı¯
    0.07
    Activations Density 0.141%

    No Known Activations