© 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. 61651
    Prev
    Next
    INDEX
    Explanations

    fields and concepts

    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
    åĨ¤
    -0.08
    amah
    -0.08
    ecto
    -0.07
    undi
    -0.07
    mä
    -0.07
    æݥ触è¿ĩ
    -0.07
    roduced
    -0.07
    uck
    -0.07
    lation
    -0.07
    sprache
    -0.07
    POSITIVE LOGITS
    æľ¬èº«å°±æĺ¯
    0.08
     inse
    0.08
    ä¸ĢéŨ
    0.08
    è§ģ人
    0.07
    +W
    0.07
    ruk
    0.07
     itself
    0.07
    ä¸įåıªæĺ¯
    0.06
    ä¸įè¨Ģ
    0.06
    oke
    0.06
    Activations Density 0.118%

    No Known Activations