© 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. 1591
    Prev
    Next
    INDEX
    Explanations

    and followed by punctuation or conjunctions

    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
    -expand
    -0.07
    åĨį说
    -0.07
    èĢĮä¸Ķæĺ¯
    -0.07
    åħ¨éĥ¨åĨħ容
    -0.06
    -exclusive
    -0.06
    åīįèĢħ
    -0.06
    entially
    -0.06
    渴
    -0.06
    æĸ¹éĿ¢
    -0.06
    heb
    -0.06
    POSITIVE LOGITS
     and
    0.11
    åĴĮ
    0.10
     vÃł
    0.10
    resp
    0.10
    à¹ģละ
    0.10
    ãĢģ
    0.09
     и
    0.09
    æľºåĴĮ
    0.09
     à¤Ķर
    0.09
    åĴĮåįİ
    0.09
    Activations Density 0.060%

    No Known Activations