© 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. 10919
    Prev
    Next
    INDEX
    Explanations

    preparation, cooking, recipes

    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
    åĵī
    -0.08
     whose
    -0.06
     infinit
    -0.06
    ä¸įè¨ĢèĢĮåĸ»
    -0.06
    èıľ
    -0.06
    åħ
    -0.06
    X
    -0.06
    azel
    -0.06
    argo
    -0.06
    åĿļæĮģä¸ĭåİ»
    -0.06
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.10
    åĤĻ
    0.09
    å°ıæľĭåıĭ们
    0.08
    亲们
    0.08
    å¤ĩ
    0.08
     prep
    0.08
     reserv
    0.07
    æħµ
    0.07
     заÑĢанее
    0.07
    kse
    0.07
    Activations Density 0.067%

    No Known Activations