© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27115
    Prev
    Next
    INDEX
    Explanations

    polynomial factorizing

    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
    اء
    -0.08
    ovi
    -0.08
    DRV
    -0.07
    unya
    -0.07
    noch
    -0.07
    FIN
    -0.07
    _To
    -0.07
    uos
    -0.07
    onz
    -0.07
    é¸¡æ¯Ľ
    -0.07
    POSITIVE LOGITS
    anken
    0.08
    åIJ´æ±Ł
    0.07
    _leave
    0.07
    æIJľ
    0.07
    ÙĨÙģ
    0.07
    arris
    0.06
    ãĥ¼ãĥĪãĥ«
    0.06
    trup
    0.06
    åIJİéĢĢ
    0.06
    åıijå±ķåĴĮ
    0.06
    Activations Density 0.003%

    No Known Activations