© 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. 45741
    Prev
    Next
    INDEX
    Explanations

    protobuf.protobuf configuration

    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
    sty
    -0.07
    ίκη
    -0.07
     ball
    -0.07
    åı¯ä¾Ŀ
    -0.07
    å®Į
    -0.07
     enumerate
    -0.06
    æģ¤
    -0.06
    ä¸īä½ĵ
    -0.06
    çIJĥçļĦ
    -0.06
     sty
    -0.06
    POSITIVE LOGITS
    reinterpret
    0.08
    æ¥ŀ
    0.07
    ients
    0.07
     взаим
    0.07
    è¿IJ
    0.07
    ESE
    0.07
    ä¸įä¼ļå½±åĵį
    0.07
    èses
    0.07
    (Temp
    0.06
    å§ijå§ij
    0.06
    Activations Density 0.001%

    No Known Activations