© 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. 9909
    Prev
    Next
    INDEX
    Explanations

    convergence

    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
    åįķå±Ĥ
    -0.07
    ÙĥÙĬÙĦ
    -0.07
    ((__
    -0.07
     ilo
    -0.06
    åĩıå°ij对
    -0.06
    æĢĿéĩı
    -0.06
    æĪij们çļĦå·¥ä½ľ
    -0.06
    éĥ¨çļĦ
    -0.06
    uter
    -0.06
    legen
    -0.06
    POSITIVE LOGITS
    ëĵł
    0.08
    绸
    0.08
    天æ°Ķé¢ĦæĬ¥
    0.08
     convergence
    0.07
     tails
    0.07
    aft
    0.07
    estan
    0.07
    olg
    0.07
     Companion
    0.07
     converge
    0.07
    Activations Density 0.004%

    No Known Activations