© 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. 44899
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or variables

    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
    ovina
    -0.08
    äºĨä¸Ģæł·
    -0.07
    åīįåIJİçļĦ
    -0.07
     Apel
    -0.07
    ovin
    -0.07
    sov
    -0.07
    æĹĹé¼ĵ
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    ovi
    -0.07
    opyright
    -0.07
    POSITIVE LOGITS
    kais
    0.08
    ionario
    0.08
    ackle
    0.08
    å°¤åħ¶æĺ¯
    0.07
    owler
    0.07
    æŶéĹ´åĨħ
    0.07
    æľĪæľĪ
    0.07
    atum
    0.07
    äºijéľĦ
    0.07
    atives
    0.07
    Activations Density 0.004%

    No Known Activations