© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    news and government titles

    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
    vad
    -0.07
     following
    -0.07
     same
    -0.07
     original
    -0.07
    -0.06
    Ù°
    -0.06
     aforementioned
    -0.06
     easiest
    -0.06
    ä¸Ģç§į
    -0.06
    ä¸Ģ个éĩįè¦ģ
    -0.06
    POSITIVE LOGITS
    æĢ§çļĦ
    0.09
    级çļĦ
    0.09
    ละ
    0.08
    åħ³äºİè¿Ľä¸ĢæŃ¥
    0.08
    .prototype
    0.08
    çļĦäºĭåĦ¿
    0.08
    ç´ļçļĦ
    0.08
    edly
    0.08
    ä½łä¸įçŁ¥éģĵ
    0.08
     ÙħعÙĬÙĨ
    0.08
    Activations Density 0.045%

    No Known Activations