© 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. 55617
    Prev
    Next
    INDEX
    Explanations

    showing or encoding output

    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
    rent
    -0.07
    æ³ķå¾ĭåĴĮ
    -0.06
    occo
    -0.06
    åĿıäºĭ
    -0.06
    averse
    -0.06
    pend
    -0.06
    iers
    -0.06
    acom
    -0.06
    hest
    -0.06
    çĥŃéŨæĸĩç«ł
    -0.06
    POSITIVE LOGITS
    çħ§æł·
    0.09
    å¦Ĥå®ŀ
    0.09
    çŁ¥åħ¶
    0.08
    igas
    0.08
    å¸IJ
    0.08
    omatis
    0.08
     ê·¸ëĮĢë¡ľ
    0.08
    æ·ĭæ¼ĵ
    0.08
    缸åºĶ
    0.07
    缸æĩī
    0.07
    Activations Density 0.080%

    No Known Activations