© 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. 31961
    Prev
    Next
    INDEX
    Explanations

    mirror, camera, sul, interest, bankruptcy, kitchen

    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
    avra
    -0.08
    åľĪçļĦ
    -0.07
    leg
    -0.07
    akan
    -0.07
    æī¿æĭħä¸ĢåĪĩ
    -0.07
    ç¿İ
    -0.07
    dj
    -0.07
    éĢģåĩº
    -0.07
    íĮ½
    -0.07
     nang
    -0.07
    POSITIVE LOGITS
    afa
    0.07
     [âĢ¦]
    0.07
    èµĸ以
    0.07
    ká
    0.07
    (er
    0.07
    uem
    0.06
    ï½ŀãĢĤ
    0.06
    ::$
    0.06
    èĢĮä»Ĭ
    0.06
    åĭŁ
    0.06
    Activations Density 1.607%

    No Known Activations