© 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. 23337
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    dition
    -0.07
    åħ¶ä¸Ń以
    -0.07
    (extra
    -0.07
    以对
    -0.07
    .TypeOf
    -0.07
    å¤
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    nost
    -0.06
    zne
    -0.06
     typealias
    -0.06
    POSITIVE LOGITS
    adox
    0.08
    ä¾ĥ
    0.07
    à¸Ńยูà¹Īà¹ģลà¹īว
    0.07
    issen
    0.07
    èĸĩèĸĩ
    0.06
    ساÙĨÛĮ
    0.06
    ubbo
    0.06
    buk
    0.06
     specified
    0.06
     supposed
    0.06
    Activations Density 0.019%

    No Known Activations