© 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. 19556
    Prev
    Next
    INDEX
    Explanations

    case selection

    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
    aceous
    -0.08
    asher
    -0.06
    à¹Ģà¸Ķียว
    -0.06
    Ĺ
    -0.06
    èijĹ
    -0.06
    ↵
    -0.06
    :"
    -0.06
    :.
    -0.06
    æĪIJ为ä¸Ģ个
    -0.06
    rey
    -0.06
    POSITIVE LOGITS
    raud
    0.08
    '][]
    0.08
    âĢ¦]
    0.08
    hci
    0.08
    OrUpdate
    0.08
     ...\
    0.08
    lei
    0.08
    %</
    0.07
    wiek
    0.07
    atorios
    0.07
    Activations Density 0.001%

    No Known Activations