© 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. 46409
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
     fr
    -0.07
    bu
    -0.06
     id
    -0.06
     g
    -0.06
    oud
    -0.06
    баÑĤ
    -0.06
     bu
    -0.06
    iru
    -0.06
    èĦ¸ä¸Ĭ
    -0.06
    æĿ¿ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    heden
    0.08
    stime
    0.08
    arik
    0.08
    ovil
    0.08
    åĴĮå¿«ä¹IJ
    0.07
    èĬ®
    0.07
     اÙĦÙĥÙĦÙħ
    0.07
    çĪ±å°Ķ
    0.07
    tright
    0.07
    ÐŁÐŁ
    0.07
    Activations Density 0.037%

    No Known Activations