© 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. 61098
    Prev
    Next
    INDEX
    Explanations

    if, than, night, contains, weapons, ifth, Green

    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
    ä¹ĭ约
    -0.08
    ÐijÐł
    -0.08
    brug
    -0.08
    ä¿ĿåĪ©
    -0.08
    ÑĢÑĥÑİ
    -0.07
    cza
    -0.07
    QRST
    -0.07
    å¿«äºĨ
    -0.07
    çĴĢ
    -0.07
    eby
    -0.07
    POSITIVE LOGITS
    isha
    0.08
    oper
    0.08
    co
    0.07
    agal
    0.07
    ier
    0.07
    éĺ³
    0.07
    å½¢
    0.07
    ä¸į误
    0.06
    arc
    0.06
    误
    0.06
    Activations Density 0.016%

    No Known Activations