© 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. 47926
    Prev
    Next
    INDEX
    Explanations

    fruit and vegetable

    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
    alk
    -0.07
     pó
    -0.06
    owitz
    -0.06
    ROM
    -0.06
    çIJĨå·¥åѦéĻ¢
    -0.06
    xt
    -0.06
    رÙģ
    -0.06
    esters
    -0.06
    δι
    -0.06
    ordes
    -0.06
    POSITIVE LOGITS
    aksim
    0.09
    usy
    0.08
     recogn
    0.08
    å¾ĢæľŁç²¾å½©
    0.08
    æľ¬çīĪ
    0.07
    ÙĨØ©
    0.07
    ëĮĢìĻĢ
    0.07
     expectedResult
    0.07
    gradu
    0.07
    _smart
    0.07
    Activations Density 0.015%

    No Known Activations