© 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. 47492
    Prev
    Next
    INDEX
    Explanations

    transitive relation or transparency

    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
     ÑĪи
    -0.08
    alap
    -0.08
    çĶŁåŃIJ女
    -0.08
    çĶµåĽ¾
    -0.07
    leur
    -0.07
    ç¼´
    -0.07
    ered
    -0.07
    ambangan
    -0.07
    æĬĬåŃ©åŃIJ
    -0.07
     Bust
    -0.07
    POSITIVE LOGITS
    æĢ§
    0.08
    æł¡
    0.07
    (chain
    0.07
    éĵ¾æĿ¡
    0.07
    åĴ¬
    0.07
     Edgar
    0.06
    _chain
    0.06
    åĶ¯
    0.06
    æŀģ强
    0.06
    extend
    0.06
    Activations Density 0.002%

    No Known Activations