© 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. 13429
    Prev
    Next
    INDEX
    Explanations

    output of node/text

    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
    olini
    -0.08
    åħ¶å®ĥåªĴä½ĵ
    -0.07
    inux
    -0.07
    ä»ĸåij½
    -0.07
    积
    -0.07
    husus
    -0.07
    clearfix
    -0.07
     tess
    -0.07
    çļĦä¸Ģçīĩ
    -0.07
    affe
    -0.07
    POSITIVE LOGITS
    minent
    0.07
    ä¸įä¼ij
    0.07
     hÃłm
    0.06
    Sessions
    0.06
    celand
    0.06
    è¿Ļ项
    0.06
    ä»»ä½ķ人
    0.06
    æį§
    0.06
    äºĶ人
    0.06
    éĤª
    0.06
    Activations Density 0.065%

    No Known Activations