© 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. 34208
    Prev
    Next
    INDEX
    Explanations

    decisions dates and citations

    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
    avern
    -0.07
     Thornton
    -0.07
    afil
    -0.07
     *(*
    -0.07
    oya
    -0.07
    æĪĸå¤ļ
    -0.06
    tora
    -0.06
    åĮ
    -0.06
    èĮģ
    -0.06
    aleza
    -0.06
    POSITIVE LOGITS
    LP
    0.08
    aderas
    0.07
    åŃĹè¯į
    0.07
    lp
    0.07
    åīį车
    0.07
    à°£
    0.07
    NX
    0.07
     genu
    0.07
     nis
    0.07
     suomi
    0.07
    Activations Density 0.047%

    No Known Activations