© 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. 26906
    Prev
    Next
    INDEX
    Explanations

    modifier keys + commands

    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
    ydi
    -0.08
    å¹´å¹´åºķ
    -0.07
    bean
    -0.07
    LLU
    -0.07
    _msgs
    -0.07
    é¢ĦæĸĻ
    -0.07
    éĥ½æĺ¯çĶ±
    -0.07
    é»ijçľ¼åľĪ
    -0.07
    yty
    -0.07
    wordpress
    -0.07
    POSITIVE LOGITS
    å¿«æį·éĶ®
    0.08
    è¾ħ
    0.08
    .ctrl
    0.07
    è¼Ķ
    0.07
    å¿«éĢŁ
    0.07
     roomId
    0.07
    åľ°èĹı
    0.07
    (KeyCode
    0.07
    èħ¾
    0.07
     ÑĢежим
    0.07
    Activations Density 0.074%

    No Known Activations