© 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. 64816
    Prev
    Next
    INDEX
    Explanations

    emphasis mine

    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
    embers
    -0.07
    ä»ĸç«ŁçĦ¶
    -0.07
    anter
    -0.07
     mex
    -0.07
    Substring
    -0.06
    ensif
    -0.06
     bound
    -0.06
    bound
    -0.06
    ä¸ĥåįģäºĮ
    -0.06
    XObject
    -0.06
    POSITIVE LOGITS
    æĶ¾è¿ĩ
    0.07
    ç§ģæľį
    0.07
     quoted
    0.07
    çĭ¬åѤ
    0.07
     emphasis
    0.07
    æİ¥ä¸ĭ
    0.07
    è¿ĩéĶĻ
    0.07
    /span
    0.07
    ãĥīãĥ¼
    0.06
     paragraph
    0.06
    Activations Density 0.035%

    No Known Activations