© 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. 49712
    Prev
    Next
    INDEX
    Explanations

    dates and lists

    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
    odia
    -0.09
    поÑĢ
    -0.08
    ugier
    -0.08
    ulté
    -0.07
    centes
    -0.07
    èĢĮä¸Ķè¦ģ
    -0.07
    èŁ¹
    -0.07
    uggy
    -0.07
    ormais
    -0.07
    vincia
    -0.07
    POSITIVE LOGITS
    å¼
    0.08
    æīĢæĥ³
    0.07
    æ¦Ĥæĭ¬
    0.06
    ason
    0.06
    滥
    0.06
    åĬ¹
    0.06
    िला
    0.06
    tl
    0.06
     CHO
    0.06
     sen
    0.06
    Activations Density 0.001%

    No Known Activations