© 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. 30084
    Prev
    Next
    INDEX
    Explanations

    dates and times followed by colons

    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
    _callbacks
    -0.07
    æĭ¾
    -0.07
    èĢ³è¾¹
    -0.07
    ĥĿ
    -0.07
    occo
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.06
    mals
    -0.06
     chÄĥng
    -0.06
    asaran
    -0.06
    onio
    -0.06
    POSITIVE LOGITS
    áĥķ
    0.07
    ndo
    0.07
    igar
    0.07
    igur
    0.07
    对åIJĦ
    0.07
    olumes
    0.07
    åŃĹçĶ»
    0.07
    è¤IJ
    0.06
    andbox
    0.06
     Ãĸr
    0.06
    Activations Density 0.116%

    No Known Activations