© 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. 21860
    Prev
    Next
    INDEX
    Explanations

    lower than, Delivery Date, licensed to, discover themselves, sorted numerically

    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
    cola
    -0.07
    ¡
    -0.07
    æŀľçĦ¶æĺ¯
    -0.07
    å§Ķåijĺä¼ļ主任
    -0.06
    visual
    -0.06
    缴æݥ就
    -0.06
    gat
    -0.06
    ought
    -0.06
    å§ĭç»Īæĺ¯
    -0.06
     Saga
    -0.06
    POSITIVE LOGITS
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    Otherwise
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    éĤ£åıĮ
    0.07
    opak
    0.07
    ä¸į妨
    0.07
    rai
    0.07
    è®
    0.07
    æļ´éľ²
    0.06
    çļĦåħ¶ä»ĸ
    0.06
    Activations Density 0.078%

    No Known Activations