© 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. 47240
    Prev
    Next
    INDEX
    Explanations

    section markers

    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
    bast
    -0.08
    önt
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
    udu
    -0.07
    æ¯Ķäºļ
    -0.07
    andr
    -0.07
    åħ¬åı¸æıIJä¾Ľ
    -0.06
    æıIJè¦ģ
    -0.06
    cest
    -0.06
    pare
    -0.06
    POSITIVE LOGITS
    ³³
    0.07
    iph
    0.07
     Âł
    0.07
    ÑģоÑĢ
    0.07
    çī¹åĪ«æĺ¯
    0.06
    éĶĭåĪ©çļĦ
    0.06
    个æľĪåīį
    0.06
    ³³³
    0.06
    å½ĵåħ¶
    0.06
    /Web
    0.06
    Activations Density 0.042%

    No Known Activations