© 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. 11227
    Prev
    Next
    INDEX
    Explanations

    Objective-C, Spring, API, XPath

    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
    åĴĮæ°´
    -0.07
    ç¾ģ
    -0.07
    æľīåı¯èĥ½æĺ¯
    -0.07
    è¯ģæĺİèĩªå·±
    -0.06
    ä»ħä»ħæĺ¯
    -0.06
    çĶ±çľģ
    -0.06
    主è¦ģæĺ¯æĮĩ
    -0.06
    å²Ń
    -0.06
    ä¾Ľå¤§å®¶åıĤèĢĥ
    -0.06
    ä»ħ代表
    -0.06
    POSITIVE LOGITS
     solito
    0.08
    详ç»ĨåĨħ容
    0.07
     assumes
    0.07
     usu
    0.07
    ิà¸ĩ
    0.06
    ellen
    0.06
     nutshell
    0.06
    yp
    0.06
    /cop
    0.06
     Usually
    0.06
    Activations Density 0.001%

    No Known Activations