© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    text formatting, metadata, or code elements

    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
     Horton
    -0.08
    ãĥ¼ãĤ¿ãĥ¼
    -0.08
    åĴĮæľīåħ³
    -0.07
    离åIJĪ
    -0.07
    opedia
    -0.07
     liá»ħu
    -0.07
    inan
    -0.07
    arka
    -0.07
    åĴĮåĨħ
    -0.07
    jam
    -0.07
    POSITIVE LOGITS
    åħ¬
    0.07
    è¾ĵåħ¥
    0.07
    ub
    0.07
    æĪĸå¤ļ个
    0.07
    ú
    0.07
     theirs
    0.06
    ached
    0.06
    æĶ¶èİ·äºĨ
    0.06
    Ãļ
    0.06
    perc
    0.06
    Activations Density 0.001%

    No Known Activations