© 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. 45320
    Prev
    Next
    INDEX
    Explanations

    works this

    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
    åįĬ
    -0.07
    説
    -0.06
    -0.06
     Tam
    -0.06
    ä¸Ģéĥ¨åĪĨ
    -0.06
    /
    -0.06
    -
    -0.06
    ↵
    -0.06
    ther
    -0.06
    _WH
    -0.06
    POSITIVE LOGITS
    ãĤĴãĤ¹ãĥĪãĥĥãĤ¯
    0.09
     вÑģÑĤÑĢеÑĩÑĥ
    0.08
    ieÅĦ
    0.08
    窥éķľ
    0.08
    cour
    0.08
    ¿
    0.08
    efon
    0.08
    cctor
    0.08
    xada
    0.08
    elmet
    0.08
    Activations Density 0.037%

    No Known Activations