© 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. 28568
    Prev
    Next
    INDEX
    Explanations

    arranged, placed, sorted, ordered, built

    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
    æĭįæĭį
    -0.08
    à¸Ĺัà¸Ļ
    -0.07
    erable
    -0.07
    igem
    -0.07
    说åĩºæĿ¥
    -0.07
    çļĦè¿ĺæľī
    -0.07
    èµ°éģį
    -0.07
    _iters
    -0.07
    horn
    -0.07
    adam
    -0.06
    POSITIVE LOGITS
    æĺ¯æĮīçħ§
    0.18
    æĮīçħ§
    0.17
    å°ĨæĮīçħ§
    0.17
    è¦ģæĮīçħ§
    0.16
    åºĶæĮīçħ§
    0.15
    åºĶå½ĵæĮīçħ§
    0.15
    æĮīåħ¶
    0.14
    ä¸¥æł¼æĮīçħ§
    0.14
    åºĶå½ĵä¾Ŀçħ§
    0.13
    æĮī
    0.13
    Activations Density 0.266%

    No Known Activations