© 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. 10050
    Prev
    Next
    INDEX
    Explanations

    de la, iazolidine

    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
    峪
    -0.08
     Pinh
    -0.07
    edt
    -0.07
    ==-
    -0.07
    .bz
    -0.07
     calci
    -0.07
    æĸĩæѦ
    -0.07
    butt
    -0.07
    eous
    -0.07
     hypoc
    -0.07
    POSITIVE LOGITS
    稳
    0.08
    stel
    0.07
     Gal
    0.07
    åŁºæķ°
    0.07
    riv
    0.07
     domination
    0.07
    ä¸īåįĥ
    0.07
    ensee
    0.07
    miar
    0.07
    å¿Ĺ
    0.07
    Activations Density 0.005%

    No Known Activations