© 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. 47797
    Prev
    Next
    INDEX
    Explanations

    numbers and lengths

    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
    çŀ©
    -0.09
    ayani
    -0.08
    è´£
    -0.08
    tpl
    -0.07
    ivil
    -0.07
    åŁºç¡ĢçłĶ究
    -0.07
    è¿Ļé¢Ĺ
    -0.07
    agni
    -0.07
    æī¬æī¬
    -0.07
    qv
    -0.07
    POSITIVE LOGITS
    éĻIJå®ļ
    0.07
    çĮ
    0.07
    cut
    0.06
    _iterator
    0.06
    ish
    0.06
    æĪijæľĢ
    0.06
    kest
    0.06
    appable
    0.06
    å¯Ĩ
    0.06
    å¯ĨéĽĨ
    0.06
    Activations Density 0.006%

    No Known Activations