© 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. 61324
    Prev
    Next
    INDEX
    Explanations

    places and groups

    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
    éĥ½æĺ¯ä¸ºäºĨ
    -0.07
    å¦Ĥåħ¶
    -0.07
    æķħäºĭæĥħèĬĤ
    -0.06
    ä¼ļé¦Ĩ
    -0.06
    æĬĽå¼ĥ
    -0.06
    äººä¸ºæľ¬
    -0.06
    åįĹèĩ³
    -0.06
    ä¸įèµ·æĿ¥
    -0.06
    /story
    -0.06
    stands
    -0.06
    POSITIVE LOGITS
    enzhen
    0.08
    PTR
    0.07
    ä¸Ĭè¿Ľ
    0.07
    åħĭæĸ¯
    0.07
    ç³»
    0.07
    -dominated
    0.06
    idd
    0.06
    åįģæľĪ
    0.06
    ison
    0.06
     biod
    0.06
    Activations Density 0.274%

    No Known Activations