© 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. 64445
    Prev
    Next
    INDEX
    Explanations

    patent numbers or mathematical expressions

    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
    zim
    -0.07
    飬
    -0.07
    ä¸½å¨ľ
    -0.07
     Zit
    -0.07
    stad
    -0.07
    cao
    -0.07
    _traits
    -0.07
    swer
    -0.07
    ENTA
    -0.07
    _DEFINED
    -0.07
    POSITIVE LOGITS
    åĩºæĿ¥åIJİ
    0.07
    áĥIJáĥłáĥĹ
    0.07
     emergence
    0.07
    åįĹèĩ³
    0.07
    ä¸Ģæ°Ķ
    0.07
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    0.06
    aderas
    0.06
    adini
    0.06
    plus
    0.06
    uxtap
    0.06
    Activations Density 0.001%

    No Known Activations