© 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. 12469
    Prev
    Next
    INDEX
    Explanations

    divided by

    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
    大å°ıå§IJ
    -0.07
    çŀ»
    -0.07
    pt
    -0.07
    jep
    -0.07
    pte
    -0.07
    egin
    -0.07
     deteri
    -0.06
    ζί
    -0.06
     settim
    -0.06
    å¿ł
    -0.06
    POSITIVE LOGITS
    éŁ³
    0.07
    绣
    0.07
     bisexual
    0.07
    .copyOf
    0.06
     incoming
    0.06
    unday
    0.06
    odate
    0.06
    Ø°
    0.06
    ẫy
    0.06
    umba
    0.06
    Activations Density 0.002%

    No Known Activations