© 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. 62782
    Prev
    Next
    INDEX
    Explanations

    a/an/part constructions

    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
    çijŀæĭī
    -0.09
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.08
    å·¥åķĨ注åĨĮåı·
    -0.08
    åľ¨åŃ¦ä¹łä¸Ń
    -0.08
    åį«çĶŁå±Ģ
    -0.08
    tÃł
    -0.08
    sä
    -0.08
    åĽŀå¸ĸ
    -0.08
    认è¯ģåķĨ家
    -0.08
    ç»ıçIJĨæĭĽèģĺ
    -0.08
    POSITIVE LOGITS
    nam
    0.06
    äºĭåĬ¡
    0.06
    M
    0.06
    att
    0.06
    æľīè¾ĥ强çļĦ
    0.06
    æĴ°åĨĻ
    0.06
    Had
    0.06
    å®ĺ
    0.06
    åıĮ
    0.06
     M
    0.06
    Activations Density 0.005%

    No Known Activations