© 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. 46791
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and laws

    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
    ©
    -0.08
    天äºĨ
    -0.07
    FOUND
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    maz
    -0.07
    éĥ½å±ŀäºİ
    -0.06
    ä¾Ŀæį®
    -0.06
    modo
    -0.06
    érico
    -0.06
    åħ¨æĸĩéĺħ读
    -0.06
    POSITIVE LOGITS
    unek
    0.08
    yron
    0.08
    enen
    0.07
    sWith
    0.07
     пÑĢимен
    0.07
    åºĶçĶ¨äºİ
    0.07
     Rear
    0.07
    yll
    0.07
    asics
    0.07
    ullo
    0.07
    Activations Density 0.012%

    No Known Activations