© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62724
    Prev
    Next
    INDEX
    Explanations

    class, kinds, spells, patients, premises, countries

    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
    utel
    -0.07
    çŁ³åĮĸ
    -0.07
     tast
    -0.07
    ire
    -0.07
    å¯¹æľªæĿ¥
    -0.07
     ÏĢαÏģε
    -0.07
    çļĦæĢ§èĥ½
    -0.07
    ottom
    -0.07
     Galler
    -0.07
    iteral
    -0.07
    POSITIVE LOGITS
    ноÑģÑı
    0.07
    æļ
    0.07
    é¡·
    0.07
     contenant
    0.07
    venz
    0.07
     empty
    0.07
    åķ¬
    0.07
    ä¸ĩæĪ·
    0.07
    çĭ¼
    0.07
     touched
    0.07
    Activations Density 0.139%

    No Known Activations