© 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. 33462
    Prev
    Next
    INDEX
    Explanations

    contents issue

    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
     lik
    -0.06
    çĮ¬
    -0.06
    åı¯åĪ©çĶ¨
    -0.06
    èĦļ
    -0.06
    ä»»ä½ķ
    -0.06
    è¦ģå¤ļ
    -0.06
    ool
    -0.06
    zna
    -0.06
    æ¸ħçĻ½
    -0.06
    鸡精
    -0.06
    POSITIVE LOGITS
    åºı
    0.08
    åºıåı·
    0.08
     âĶľâĶĢâĶĢ
    0.08
    丽ä¸Ŀ
    0.08
    æľĢæĸ°è¯Ħ论
    0.07
    彬
    0.07
    DebugEnabled
    0.07
    -li
    0.07
    大éĥ¨åĪĨéĥ½æĺ¯
    0.07
    [List
    0.07
    Activations Density 0.303%

    No Known Activations