© 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. 18249
    Prev
    Next
    INDEX
    Explanations

    a quantity or type

    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
    umbo
    -0.08
    æIJŃä¸Ĭ
    -0.08
    èģĶè½´
    -0.08
    Selectable
    -0.07
    çīĪæĿĥåĿĩ
    -0.07
    god
    -0.07
    çļ®çĤİ
    -0.07
    é¼ĵé£İæľº
    -0.07
    avigator
    -0.07
    Aws
    -0.07
    POSITIVE LOGITS
    ä¸ĺ
    0.08
    oks
    0.08
    rud
    0.08
    miner
    0.07
    æŁIJ
    0.07
    uco
    0.07
     mineral
    0.07
    min
    0.06
    пен
    0.06
     Leng
    0.06
    Activations Density 0.024%

    No Known Activations