© 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. 30874
    Prev
    Next
    INDEX
    Explanations

    next/previous navigation

    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
    ä¸Ī
    -0.07
    åıĺæĢģ
    -0.07
    essed
    -0.06
     Campan
    -0.06
    æĬ«çĿĢ
    -0.06
    illin
    -0.06
    亩
    -0.06
    -public
    -0.06
    çĭ¬
    -0.06
    ÙħÙĬز
    -0.06
    POSITIVE LOGITS
    æĵį
    0.10
    缸éĤ»
    0.10
    (direction
    0.09
    æĸ¹åIJijçļĦ
    0.09
    æĸ¹åIJij
    0.09
    移åĭķ
    0.08
    SHIFT
    0.08
    (shift
    0.08
    åīįè¿Ľ
    0.08
    åı¯å¢ŀåĬł
    0.08
    Activations Density 0.096%

    No Known Activations