© 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. 60785
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and numbers

    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
    æijĺç¼ĸ
    -0.08
    portun
    -0.08
    zicht
    -0.08
    é«ĺå¯Ĩ
    -0.07
    Globals
    -0.07
    ible
    -0.07
    Notifier
    -0.07
    å±ħæĺĵ
    -0.07
    .beh
    -0.07
    æĨ¤
    -0.07
    POSITIVE LOGITS
    átk
    0.07
    IAN
    0.07
    å½¼
    0.06
    æ§
    0.06
    ×ŀ×Ļ×ĵ
    0.06
    ç¾İ人
    0.06
     sui
    0.06
    ONO
    0.06
    ellate
    0.06
    æĺ¯æīĢæľī
    0.06
    Activations Density 0.008%

    No Known Activations