© 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. 17314
    Prev
    Next
    INDEX
    Explanations

    implementation and adoption

    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
    enaus
    -0.08
    rous
    -0.07
    enge
    -0.07
    解å°ģ
    -0.07
    æ¶Ī磨
    -0.07
    Manip
    -0.07
    åĴĮç»´çĶŁç´ł
    -0.07
    itzt
    -0.07
    çķĻç»Ļ
    -0.07
    .allocate
    -0.07
    POSITIVE LOGITS
    åĴĮæݨ广
    0.12
    æݨ广
    0.10
    /install
    0.09
     widespread
    0.09
    åĴĮå®ŀæĸ½
    0.08
    å®ŀæĸ½
    0.08
    æĻ®åıĬ
    0.08
    æĸ°çļĦ
    0.08
    çļĦä¸Ģå¥Ĺ
    0.08
    è§ģæķĪ
    0.08
    Activations Density 0.199%

    No Known Activations