© 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. 12338
    Prev
    Next
    INDEX
    Explanations

    assembly information

    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
    BOUND
    -0.07
    驱车
    -0.07
    æ¾³åħĥ
    -0.07
    peror
    -0.07
    ä¼ģä¸ļåıĹçĽĬ
    -0.07
    lopedia
    -0.07
    toa
    -0.07
    èĵĦ
    -0.07
    æŀ
    -0.07
    .compat
    -0.07
    POSITIVE LOGITS
    iss
    0.09
    ļĮ
    0.08
    ek
    0.06
    er
    0.06
    irs
    0.06
    ix
    0.06
    Jet
    0.06
     Math
    0.06
    ks
    0.06
    ius
    0.06
    Activations Density 0.062%

    No Known Activations