© 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. 20067
    Prev
    Next
    INDEX
    Explanations

    sub-items, sub-categories, sub-phases

    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
    åłĤåłĤ
    -0.08
    ä¸įè¿ľ
    -0.08
    TEGR
    -0.08
    hint
    -0.07
    isto
    -0.07
    bere
    -0.07
    atos
    -0.07
    owska
    -0.07
    سÙĨ
    -0.07
    åı¦å¤ĸä¸Ģç§į
    -0.07
    POSITIVE LOGITS
    åŃIJ
    0.11
     sub
    0.11
    (sub
    0.09
     subsection
    0.09
    çļĦåŃIJ
    0.08
    ä¹ĭä¸ĢçļĦ
    0.08
    å°ı
    0.08
    ãģ«åĪĨ
    0.08
    /sub
    0.08
    utch
    0.08
    Activations Density 0.107%

    No Known Activations