© 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. 33469
    Prev
    Next
    INDEX
    Explanations

    citation markers and parenthetical material

    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
    k
    -0.07
    ango
    -0.07
    ä»»
    -0.06
    C
    -0.06
    èĢĮå·²
    -0.06
    μιÏĥ
    -0.06
    è´§
    -0.06
    åijµ
    -0.05
    ANGO
    -0.05
    ä¸Ńè·¯
    -0.05
    POSITIVE LOGITS
     forthcoming
    0.09
    éħ¸éĴ¾
    0.08
    جÙĬ
    0.08
    lett
    0.08
    &w
    0.08
    丽èİİ
    0.08
    corso
    0.08
    apk
    0.08
    adir
    0.08
    aik
    0.08
    Activations Density 0.047%

    No Known Activations