© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    German prefix "se"

    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
     siÄĻ
    -0.09
    ìį¨
    -0.09
    ajib
    -0.08
     ÑģебÑı
    -0.08
     sich
    -0.08
    jenigen
    -0.07
    ized
    -0.07
    ekyll
    -0.07
     './../
    -0.07
    tons
    -0.07
    POSITIVE LOGITS
    ergestellt
    0.09
    culares
    0.09
    igneur
    0.08
    mployee
    0.08
     ÑģлÑĥÑĩи
    0.07
    RLF
    0.07
     rivolg
    0.07
    /is
    0.07
    OrElse
    0.07
    leccion
    0.07
    Activations Density 0.036%

    No Known Activations