© 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. 16374
    Prev
    Next
    INDEX
    Explanations

    list is endless

    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
    empi
    -0.08
    áĥĺáĥª
    -0.08
    asant
    -0.08
    ugt
    -0.07
    åĬ©äºİ
    -0.07
     ")"
    -0.07
    ä¸Ģç½ij
    -0.07
    ãģ¾ãģ¾ãģ§
    -0.07
    对她çļĦ
    -0.07
    \Migrations
    -0.07
    POSITIVE LOGITS
    :
    0.09
    ï¼ļ
    0.08
    èĶļ
    0.07
    ango
    0.07
    fre
    0.07
    æĸĩåįļ
    0.06
    Fre
    0.06
    ayed
    0.06
     fre
    0.06
    claim
    0.06
    Activations Density 0.001%

    No Known Activations