© 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. 29815
    Prev
    Next
    INDEX
    Explanations

    quotation marks and speech

    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
    濯
    -0.07
    åħĪå¾Ĺ
    -0.06
    oner
    -0.06
     immedi
    -0.06
    æĿ¡æĿ¡
    -0.06
    Proc
    -0.06
    延
    -0.06
    ä¹Ī
    -0.06
    _pairs
    -0.06
    欺
    -0.06
    POSITIVE LOGITS
     blah
    0.08
    æĢ»åĨłåĨĽ
    0.08
     Beri
    0.07
    æĢ»ä¹ĭ
    0.07
     Uw
    0.07
    å¸ĮæľĽ
    0.07
    æĸĩç¬Ķ
    0.07
    idade
    0.07
    满åłĤ
    0.07
    èķ
    0.07
    Activations Density 0.099%

    No Known Activations