© 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. 11545
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    å®Īåį«
    -0.07
    ç»´äºļ
    -0.07
    ÑĢÑĥпп
    -0.07
    æ´¾
    -0.06
    ãģ¼ãģĨ
    -0.06
    åIJİ继
    -0.06
    jes
    -0.06
    继
    -0.06
    asis
    -0.06
    rowned
    -0.06
    POSITIVE LOGITS
    类似çļĦ
    0.08
    udd
    0.07
    åIJĮæł·çļĦ
    0.07
    æīįæĺ¯æľĢ
    0.07
    èĹ
    0.07
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.07
    à¸Ľà¸¥
    0.07
    usting
    0.07
    .compare
    0.07
     serupa
    0.07
    Activations Density 0.174%

    No Known Activations