© 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. 63169
    Prev
    Next
    INDEX
    Explanations

    describes states or changes

    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
    beck
    -0.08
    å®ķ
    -0.08
    ivec
    -0.08
    以åIJİçļĦ
    -0.07
     onward
    -0.07
    礼
    -0.07
    theid
    -0.07
    综åIJĪ楼
    -0.07
    ContentSize
    -0.07
    åªĽ
    -0.07
    POSITIVE LOGITS
    éļıåľ°
    0.08
    åıĺåĮĸæĥħåĨµ
    0.07
    ä¼ļéļıçĿĢ
    0.07
    éļıé£İ
    0.07
    åįķè°ĥ
    0.07
    åıĺåĮĸçļĦ
    0.07
    éļı
    0.07
     always
    0.07
    ä¼ļåĽłä¸º
    0.06
    åľ¨æ¯ı个
    0.06
    Activations Density 0.047%

    No Known Activations