© 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. 33695
    Prev
    Next
    INDEX
    Explanations

    metal-organic frameworks

    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
    ãĥŁãĥ¼
    -0.08
    ç¥Ł
    -0.08
    ä¸įåıij
    -0.08
    夫
    -0.08
    夫çļĦ
    -0.07
    PIC
    -0.07
    éĢ»
    -0.07
    elj
    -0.07
    æĶ¯
    -0.07
    ãĤ¬ãĤ¤
    -0.07
    POSITIVE LOGITS
    ä¸İä¼łç»Ł
    0.08
    agu
    0.08
     lament
    0.07
    uha
    0.07
     ease
    0.07
     promising
    0.07
     Okt
    0.07
    å°ijçĪ·
    0.06
    ettel
    0.06
     academia
    0.06
    Activations Density 0.050%

    No Known Activations