© 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. 38160
    Prev
    Next
    INDEX
    Explanations

    shapes of structures

    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
    ä¹ĭæĢ¥
    -0.08
    agal
    -0.08
    ÙĨÙĬا
    -0.08
    æµ·éģĵ
    -0.07
    arian
    -0.07
    à§ģà¦ķ
    -0.07
    iesel
    -0.07
    ilos
    -0.07
    vera
    -0.07
    _EXIST
    -0.07
    POSITIVE LOGITS
    -ish
    0.07
    å½¢çļĦ
    0.06
    -like
    0.06
    éĮ¯
    0.06
     gespre
    0.06
     advisers
    0.06
    обÑĢаз
    0.06
    ansch
    0.06
    lear
    0.06
    xon
    0.06
    Activations Density 0.001%

    No Known Activations