© 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. 61503
    Prev
    Next
    INDEX
    Explanations

    provided by, copyright, notice

    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
    ray
    -0.07
    å¼ı
    -0.07
    isht
    -0.07
    ä¸į失
    -0.06
    æĽ´è¡£
    -0.06
    è½
    -0.06
     Cabr
    -0.06
    mit
    -0.06
    :\/\/
    -0.06
    æıIJä¾Ľä¸ĢäºĽ
    -0.05
    POSITIVE LOGITS
    ানা
    0.08
    åħħå®ŀ
    0.08
    klam
    0.08
    涧
    0.08
    vás
    0.08
    满满
    0.07
    linger
    0.07
    kla
    0.07
    vier
    0.07
    минÑĥ
    0.07
    Activations Density 0.027%

    No Known Activations