© 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. 45527
    Prev
    Next
    INDEX
    Explanations

    numbers and characters

    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
    empel
    -0.07
    вки
    -0.07
    å°±åı«
    -0.07
    opol
    -0.07
    atch
    -0.07
    åĨį说äºĨ
    -0.07
    表çļĦ
    -0.07
    IKE
    -0.07
     âĵĺ
    -0.06
    inna
    -0.06
    POSITIVE LOGITS
    åıªä»£è¡¨
    0.10
    è¿Ļ个æķ°åŃĹ
    0.08
    åı¯èĥ½æĺ¯åĽłä¸º
    0.08
    å·¥ä½ľåĪ¶
    0.08
    éĤ£æĺ¯åĽłä¸º
    0.07
     иÑģÑħодÑı
    0.07
    å¾Īåı¯èĥ½æĺ¯
    0.07
    å¾·æĻº
    0.07
    èĢĮæĺ¯åĽłä¸º
    0.07
     stemmed
    0.07
    Activations Density 0.012%

    No Known Activations