© 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. 25972
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers and symbols

    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
    arshal
    -0.08
    æµij
    -0.08
    illen
    -0.08
    æĤłä¹ħ
    -0.08
    ains
    -0.08
     frau
    -0.07
    Sell
    -0.07
    çªĿ
    -0.07
    汶
    -0.07
    è°ļ
    -0.07
    POSITIVE LOGITS
    åħ¨éĽĨ
    0.08
    pow
    0.07
    REAM
    0.06
     Fusion
    0.06
     fused
    0.06
     fusion
    0.06
    ream
    0.06
    ä¸ĢèĤ¡
    0.06
    æīĢæľīçļĦ
    0.06
    atan
    0.06
    Activations Density 0.088%

    No Known Activations