© 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. 49823
    Prev
    Next
    INDEX
    Explanations

    ontology, theology, metaphysics

    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
    å¨Ł
    -0.07
    ulangan
    -0.07
    æķ°æį®ç»Łè®¡
    -0.06
     administr
    -0.06
    Scaled
    -0.06
    åIJĥ好
    -0.06
    yez
    -0.06
    æľ¬æ³ķ
    -0.06
    burgh
    -0.06
    ittest
    -0.06
    POSITIVE LOGITS
     underlying
    0.08
    åĴĮè¡Į为
    0.08
    æŀĦæŀ¶
    0.08
    åĴĮæĵįä½ľ
    0.08
    -lite
    0.08
    omy
    0.07
    建æŀĦ
    0.07
    ëħIJ
    0.07
    eggia
    0.07
    acha
    0.07
    Activations Density 0.018%

    No Known Activations