© 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. 3124
    Prev
    Next
    INDEX
    Explanations

    deals, assembly, method, hypothesis, article, message, plan, concept, group

    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
    porn
    -0.08
    erbe
    -0.07
    ãĢģ
    -0.07
    ç«¥éŀĭ
    -0.07
    åĽ½åħ¬
    -0.06
    jedn
    -0.06
    /jav
    -0.06
    å¾·åŁº
    -0.06
    eiro
    -0.06
    andom
    -0.06
    POSITIVE LOGITS
    à¦Łà¦¿
    0.08
    温度åĴĮ
    0.07
    ç»´æĬ¤åĴĮ
    0.07
     sudd
    0.07
    оло
    0.07
    åĨħ容åĴĮ
    0.06
    äºijéľĦ
    0.06
    çļĦ人åĴĮ
    0.06
    strup
    0.06
    为çĶŁ
    0.06
    Activations Density 0.100%

    No Known Activations