© 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. 61213
    Prev
    Next
    INDEX
    Explanations

    constraint, lapse, problem, equation

    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
    å°ıåĪ°
    -0.08
    bie
    -0.07
    indo
    -0.07
     Lonely
    -0.07
    ä»İå°ı
    -0.07
    æľ¬ç¤¾
    -0.07
    丢
    -0.07
    åĩ¡
    -0.06
    黯çĦ¶
    -0.06
    anser
    -0.06
    POSITIVE LOGITS
    physics
    0.08
     physics
    0.08
     slab
    0.08
    纲è¦ģ
    0.08
    æĺŁç©º
    0.07
    æĬĬåŃ©åŃIJ
    0.07
    çļĦ大èĦij
    0.07
    Spin
    0.07
     momentum
    0.07
    Eval
    0.07
    Activations Density 0.003%

    No Known Activations