© 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. 27883
    Prev
    Next
    INDEX
    Explanations

    copy of license

    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
    cliffe
    -0.07
    Associ
    -0.07
    bench
    -0.07
    odka
    -0.07
    ascar
    -0.07
    roud
    -0.07
     bench
    -0.06
    pons
    -0.06
    ä¼Ļ
    -0.06
    api
    -0.06
    POSITIVE LOGITS
    æľ¬æ³ķ
    0.08
    å¦Ĥæľīä¾µæĿĥ请èģĶç³»åĪłéĻ¤
    0.07
    沦
    0.07
    +)/
    0.07
    iné
    0.07
    ItemAt
    0.07
    øb
    0.07
    OCA
    0.07
    ãģ¾ãģĦ
    0.07
    cxx
    0.07
    Activations Density 0.664%

    No Known Activations