© 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. 11316
    Prev
    Next
    INDEX
    Explanations

    Brusselback Cahalan Derengoski Kelley

    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
    æĸ¹éĿ¢
    -0.07
    boom
    -0.06
    /dev
    -0.06
    alin
    -0.06
    _STATS
    -0.06
    å½Ŀ
    -0.06
    ente
    -0.06
    ä¸įèĥ½
    -0.06
    aft
    -0.06
     nanti
    -0.06
    POSITIVE LOGITS
    ัà¸ģ
    0.08
    vist
    0.07
    icata
    0.07
    imens
    0.07
    isata
    0.07
    aks
    0.07
    olato
    0.07
    _magic
    0.07
    alian
    0.07
    itre
    0.07
    Activations Density 0.005%

    No Known Activations