© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48476
    Prev
    Next
    INDEX
    Explanations

    urocutaneous flap

    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
     inf
    -0.07
    ç¦
    -0.07
    ç¥
    -0.06
    geist
    -0.06
    =en
    -0.06
    æµ
    -0.06
    åĮł
    -0.06
     Muk
    -0.06
    .inline
    -0.06
    å¤ļåĬł
    -0.06
    POSITIVE LOGITS
    tvr
    0.08
    TPL
    0.08
    窪
    0.07
    à¥Ĥम
    0.07
    ocere
    0.07
    ãĤ¦ãĥ³
    0.07
    lave
    0.07
    æīĭæľºæ¸¸æĪı
    0.07
    æīij
    0.07
    indr
    0.07
    Activations Density 0.929%

    No Known Activations