© 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. 62453
    Prev
    Next
    INDEX
    Explanations

    `pair`, `keys`, `index`, `video`, `_DATE`

    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
    ãĤĪãĤį
    -0.08
    kev
    -0.07
    [min
    -0.07
     nomin
    -0.07
    itan
    -0.07
    sons
    -0.06
    uben
    -0.06
    รม
    -0.06
    çļĦ亲
    -0.06
    DataManager
    -0.06
    POSITIVE LOGITS
    ä¸Ģåı¥è¯Ŀ
    0.08
    åĮħæĭ¬äºĨ
    0.08
    empi
    0.07
    åĮħåIJ«äºĨ
    0.07
    åĮħæĭ¬
    0.07
    åħ¶ä¸ŃåĮħæĭ¬
    0.07
     massac
    0.07
    ologue
    0.07
    including
    0.07
    空éĹ´çļĦ
    0.07
    Activations Density 0.082%

    No Known Activations