© 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. 12340
    Prev
    Next
    INDEX
    Explanations

    letters, numbers, or days followed by punctuation

    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
    æĬĺä¸į
    -0.10
    åīį人
    -0.08
    /Card
    -0.07
    rive
    -0.07
    好康
    -0.07
    èĢĮæĺĵ
    -0.07
     Camp
    -0.07
    irage
    -0.07
    æĸ¹å¼ı使çĶ¨
    -0.07
    ogh
    -0.07
    POSITIVE LOGITS
    nitz
    0.07
     similarly
    0.07
    æĢİä¹ĪäºĨ
    0.07
    лÑıн
    0.07
    é¾Ħ
    0.07
    -bottom
    0.06
     ultim
    0.06
     tall
    0.06
    lega
    0.06
    bottom
    0.06
    Activations Density 0.001%

    No Known Activations