© 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. 34509
    Prev
    Next
    INDEX
    Explanations

    Jab al, PE, org

    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
    luss
    -0.06
    åıªä»£è¡¨
    -0.06
     opts
    -0.06
    yclopedia
    -0.06
     getWindow
    -0.06
    oland
    -0.06
    ArrayOf
    -0.06
     SPDX
    -0.05
    engel
    -0.05
    ewa
    -0.05
    POSITIVE LOGITS
    igger
    0.08
    enburg
    0.08
    æĪijå½ĵæŶ
    0.07
    izon
    0.07
    á»ķi
    0.07
    pil
    0.07
    å½ĵæŶçļĦ
    0.07
    JE
    0.07
    apura
    0.07
    çİ°åľ¨çľĭæĿ¥
    0.07
    Activations Density 0.197%

    No Known Activations