© 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. 11671
    Prev
    Next
    INDEX
    Explanations

    ViewController.ViewController

    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
    che
    -0.07
    ker
    -0.07
    æĻ´å¤©
    -0.07
    üst
    -0.06
    ridge
    -0.06
    ibur
    -0.06
    kamp
    -0.06
    ringer
    -0.06
    uctive
    -0.06
    issen
    -0.06
    POSITIVE LOGITS
    æĥ£
    0.08
    æĭīåħĭ
    0.08
    æ¯Ķäºļ
    0.07
    ogle
    0.07
    å°ıä¸ij
    0.07
    çĮĿæŃ»
    0.07
    -${
    0.07
    꽤
    0.07
    esting
    0.07
     empre
    0.06
    Activations Density 0.037%

    No Known Activations