© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    NOT abusive

    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
    åħ¹
    -0.08
    为è°ģ
    -0.07
    åĩºå¤´
    -0.07
     Hamb
    -0.07
    amar
    -0.07
    inbox
    -0.06
    ä½łæ²¡
    -0.06
     Fle
    -0.06
    ex
    -0.06
    urat
    -0.06
    POSITIVE LOGITS
    à¸ķรี
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    .helper
    0.07
    ä¼ĺåĮĸçļĦ
    0.06
    lds
    0.06
    èĮĥæĸĩç½ij
    0.06
    æĢĿèĢĥ
    0.06
    iin
    0.06
    zim
    0.06
    egg
    0.06
    Activations Density 0.007%

    No Known Activations