© 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. 63837
    Prev
    Next
    INDEX
    Explanations

    FakePost, .generated, posts

    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
     liá»ĩu
    -0.07
    åģľåľ¨
    -0.06
    llib
    -0.06
     Venezia
    -0.06
    оÑıÑĤ
    -0.06
    åij¨è¾¹çݯå¢ĥ
    -0.06
    ...</
    -0.06
    åIJĨ
    -0.06
    妮
    -0.06
    apes
    -0.06
    POSITIVE LOGITS
    ingang
    0.08
    Ù°
    0.07
    mana
    0.07
    è½
    0.07
     postings
    0.07
    ä¸įå½Ĵ
    0.07
    .generated
    0.07
    éģĵåºľ
    0.07
    _scal
    0.07
     posts
    0.07
    Activations Density 0.001%

    No Known Activations