© 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. 21971
    Prev
    Next
    INDEX
    Explanations

    kernel and fiber products

    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
     Pob
    -0.07
    è´¹æŶ
    -0.07
    eter
    -0.07
    gi
    -0.07
    æĸĩä¸ŃçļĦ
    -0.06
     retrieved
    -0.06
     themselves
    -0.06
    dy
    -0.06
    Ľ
    -0.06
    義
    -0.06
    POSITIVE LOGITS
    å¾Īæ·±
    0.08
    ลึà¸ģ
    0.08
    ikh
    0.08
    lež
    0.07
    iminal
    0.07
    à¸ķà¹Į
    0.07
    FromClass
    0.07
    窿
    0.07
    ุ
    0.07
    ÄIJT
    0.07
    Activations Density 0.003%

    No Known Activations