© 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. 56912
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and divisions

    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
     entreprene
    -0.08
    _SUITE
    -0.07
    è¿ĩå¾Ĺ
    -0.07
    IGE
    -0.07
    amá
    -0.07
    æīĢ幸
    -0.07
    _CASE
    -0.07
    aper
    -0.07
    ä½IJ
    -0.07
     Cutter
    -0.07
    POSITIVE LOGITS
    ds
    0.07
    Pes
    0.07
     Fre
    0.07
    éĻµ
    0.07
    æĺ¯æĪij们çļĦ
    0.06
    osso
    0.06
    죽
    0.06
     Tre
    0.06
    éĩįçĤ¹
    0.06
    L
    0.06
    Activations Density 0.034%

    No Known Activations