© 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. 51080
    Prev
    Next
    INDEX
    Explanations

    amounts and levels

    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
    odom
    -0.08
    emos
    -0.07
    olas
    -0.07
    inde
    -0.07
    кÑĢе
    -0.07
    agod
    -0.07
    ilhar
    -0.07
    trag
    -0.07
     reaj
    -0.07
    ounty
    -0.07
    POSITIVE LOGITS
    æĭ©
    0.07
    åħ¥åº§
    0.06
    å½¢å¼ıçļĦ
    0.06
    ä¸įåIJĮç¨ĭ度
    0.06
     replacement
    0.06
    éĻĮçĶŁ
    0.06
     mild
    0.06
    è§
    0.06
    statt
    0.06
     pers
    0.06
    Activations Density 0.189%

    No Known Activations