© 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. 39492
    Prev
    Next
    INDEX
    Explanations

    new physics

    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
     consign
    -0.09
    oges
    -0.08
    mpeg
    -0.08
    ä¸į移
    -0.08
    éĶĢ
    -0.08
    åĭ¤
    -0.08
     greve
    -0.08
    asename
    -0.08
     hort
    -0.07
    èIJ¥éĢłäºĨ
    -0.07
    POSITIVE LOGITS
    è¿ĺä¸įçŁ¥éģĵ
    0.08
     theories
    0.08
    è¯ķåĽ¾
    0.07
    äºŁ
    0.07
     reconc
    0.07
     somehow
    0.07
    ç»Īæŀģ
    0.07
    èŀįåIJĪçļĦ
    0.07
    çłĶ究é¢ĨåŁŁ
    0.07
    å¥
    0.07
    Activations Density 0.019%

    No Known Activations