© 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. 55887
    Prev
    Next
    INDEX
    Explanations

    phoneme, conjunctiva, parish, paradigm, cells, Metadata, matter, warehouse, record

    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
    ibat
    -0.08
    -thumbnails
    -0.07
    -night
    -0.07
    主è¦ģ表çİ°åľ¨
    -0.06
    alfa
    -0.06
    主è¦ģä½ĵçİ°åľ¨
    -0.06
    alian
    -0.06
    uition
    -0.06
    ãģ£ãģįãĤĬ
    -0.06
    czyn
    -0.06
    POSITIVE LOGITS
    æĺ¯åħ·æľī
    0.08
    ÐijÐł
    0.07
    æĺ¯åħ¬åı¸
    0.07
    лÑıÑĤ
    0.07
    APON
    0.07
     appunto
    0.07
    髦
    0.07
    èĶ¼
    0.07
    åħ¬åı¸åIJij
    0.07
    ìĿ´ëŀĢ
    0.06
    Activations Density 0.050%

    No Known Activations