© 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. 8560
    Prev
    Next
    INDEX
    Explanations

    decomposition, theory, dependencies

    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
    åĪĽç«ĭäºİ
    -0.08
    ekyll
    -0.08
    èĬĿ
    -0.08
    ostr
    -0.08
     Folg
    -0.08
    adian
    -0.07
    uncio
    -0.07
     adaptación
    -0.07
    ɵ
    -0.07
    ositÃł
    -0.07
    POSITIVE LOGITS
    åĪĨ解
    0.09
    æįIJ
    0.08
     decomposition
    0.08
     disjoint
    0.08
    欢
    0.07
     Chance
    0.07
     rép
    0.07
    éķľ
    0.07
     repeats
    0.07
     repetition
    0.07
    Activations Density 0.002%

    No Known Activations