© 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. 30517
    Prev
    Next
    INDEX
    Explanations

    names and numbers

    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
    ADI
    -0.08
    çī¹åĭĴ
    -0.08
    heck
    -0.08
     вдÑĢÑĥг
    -0.08
    èĢĥè¯ķ大纲
    -0.07
    åıĪä¸įèĥ½
    -0.07
    /documentation
    -0.07
    æĪij们ä¼ļåľ¨
    -0.07
    ilot
    -0.07
     remb
    -0.07
    POSITIVE LOGITS
    ä¹Łå°±æĺ¯
    0.11
    åį³
    0.10
    åį³åľ¨
    0.10
    éĤ£å°±æĺ¯
    0.10
     yaitu
    0.09
    åį³ä»¥
    0.09
     aka
    0.09
     eli
    0.08
     czyli
    0.08
    åį³åĪ°
    0.08
    Activations Density 0.008%

    No Known Activations