© 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. 58177
    Prev
    Next
    INDEX
    Explanations

    genus *Acer*

    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
    mage
    -0.07
    ä¸įåı¯åıĬ
    -0.07
    æ³¼
    -0.07
    è¿Ļ人
    -0.06
    tru
    -0.06
    è¿Ļ个人
    -0.06
    åĩĿ
    -0.06
     Kumar
    -0.06
    obel
    -0.06
    uable
    -0.06
    POSITIVE LOGITS
    pecies
    0.08
    ukes
    0.08
    geno
    0.07
    ères
    0.07
    åIJĦ家
    0.07
    домо
    0.07
    ehl
    0.07
    ×Ļ×Ļ
    0.07
    æg
    0.07
    δεÏĤ
    0.07
    Activations Density 0.065%

    No Known Activations