© 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. 16339
    Prev
    Next
    INDEX
    Explanations

    symmetry and geometry

    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
    æļ
    -0.09
    ק×Ķ
    -0.08
    åħ¥åºĵ
    -0.08
    iau
    -0.08
    zé
    -0.08
    Ĭ
    -0.08
     piet
    -0.08
    åįĹåĽ½
    -0.07
    å¹ħ
    -0.07
    éĹº
    -0.07
    POSITIVE LOGITS
    ë¬ĺ
    0.07
     rÃŃg
    0.07
     collapsed
    0.07
    ardon
    0.07
    .nodeType
    0.06
    transition
    0.06
     Huck
    0.06
    EventListener
    0.06
     liberated
    0.06
     geometry
    0.06
    Activations Density 0.003%

    No Known Activations