© 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. 2172
    Prev
    Next
    INDEX
    Explanations

    r followed by specific events/errors

    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
    èĿ
    -0.07
    udios
    -0.06
    /********
    -0.06
    /
    -0.06
    заÑĢ
    -0.06
    ק×Ļ
    -0.06
    erver
    -0.06
    èĩªè´¹
    -0.06
    cope
    -0.06
    eleg
    -0.06
    POSITIVE LOGITS
    kje
    0.08
    åħ¨éĺŁ
    0.08
    ÖĦ
    0.08
    oser
    0.08
    æĪIJæ¸Ŀ
    0.07
    ==='
    0.07
    isien
    0.07
    çĪĨçĻ¼
    0.07
     handful
    0.07
    orem
    0.07
    Activations Density 0.001%

    No Known Activations