© 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. 31610
    Prev
    Next
    INDEX
    Explanations

    code variable declarations

    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
    oust
    -0.08
    andal
    -0.07
    Õº
    -0.07
    emony
    -0.07
    ég
    -0.07
    atar
    -0.07
    _None
    -0.07
    æīĵæİī
    -0.07
    æĢĴæĶ¾
    -0.07
    alous
    -0.07
    POSITIVE LOGITS
     reform
    0.07
    ä¹ĥ
    0.06
    dei
    0.06
    reform
    0.06
    æıIJ
    0.06
    _ENCODING
    0.06
    &C
    0.06
    äºİæĺ¯
    0.06
    å¾ĹåĪ©
    0.06
    ابع
    0.06
    Activations Density 0.027%

    No Known Activations