© 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. 64450
    Prev
    Next
    INDEX
    Explanations

    suffix "-able"

    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
    åħ¶æŀĹ
    -0.07
    íĮħ
    -0.07
    ynchronously
    -0.07
    ÄįetnÄĽ
    -0.06
    æĬ½ç©º
    -0.06
    çĸ¥
    -0.06
    irs
    -0.06
    .require
    -0.06
    иÑģк
    -0.06
    arrer
    -0.06
    POSITIVE LOGITS
    sic
    0.08
    çļĦ说æ³ķ
    0.08
    类似äºİ
    0.07
    类似
    0.07
    ogo
    0.07
     somewhere
    0.07
    æĺ¯ä»Ģä¹Ī
    0.07
    åIJ¬èµ·æĿ¥
    0.07
    说æ³ķ
    0.07
    would
    0.07
    Activations Density 0.065%

    No Known Activations