© 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. 42598
    Prev
    Next
    INDEX
    Explanations

    progression. aid. state. bending. EU. gone

    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
    éĶģ骨
    -0.07
    apan
    -0.06
     sidel
    -0.06
    ãĥīãĥ¼
    -0.06
    isi
    -0.06
    áĥIJáĥķ
    -0.06
    第ä¸Ģ件äºĭ
    -0.06
     Channel
    -0.06
    isir
    -0.06
     sink
    -0.06
    POSITIVE LOGITS
     originally
    0.13
    åİŁåħĪ
    0.11
     initially
    0.11
    åİŁæľ¬
    0.11
    åİŁæĿ¥
    0.11
    åİŁæľ¬æĺ¯
    0.11
     Initially
    0.10
     изнаÑĩалÑĮно
    0.10
    åİŁæľ¬çļĦ
    0.10
    ä½Ĩçİ°åľ¨
    0.10
    Activations Density 0.311%

    No Known Activations