© 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. 39288
    Prev
    Next
    INDEX
    Explanations

    car types and brands

    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
    çĽĪçĽĪ
    -0.07
    åį§
    -0.07
    è¡«
    -0.07
    æĹĹ
    -0.06
    丸
    -0.06
    forth
    -0.06
    inar
    -0.06
    pom
    -0.06
    çĺ¢
    -0.06
    è´®
    -0.06
    POSITIVE LOGITS
    åk
    0.09
    ä¹ĭä¸ĢçļĦ
    0.09
    åĴĮç²¾ç¥ŀ
    0.08
    ä¹ĭä¸Ģæĺ¯
    0.08
    伯æģ©
    0.08
    YPE
    0.08
    URRE
    0.08
    åĴĮæķĻèĤ²
    0.08
    åĴĮèĶ¬èıľ
    0.08
    ãģ®ç¨®é¡ŀ
    0.08
    Activations Density 0.028%

    No Known Activations