© 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. 31885
    Prev
    Next
    INDEX
    Explanations

    common word endings

    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
    elaar
    -0.10
    goed
    -0.09
    éri
    -0.09
    ÙħÙĩ
    -0.09
    eiro
    -0.08
    bergen
    -0.08
    wana
    -0.08
    æľ¬ç½ij转载
    -0.08
    ignum
    -0.08
    æīĢå±ŀåĪĨç±»
    -0.08
    POSITIVE LOGITS
    人
    0.06
    en
    0.06
    0.06
    est
    0.06
    yg
    0.05
     os
    0.05
    et
    0.05
    ìĭł
    0.05
    ÙĨ
    0.05
    uÃŁ
    0.05
    Activations Density 0.004%

    No Known Activations