© 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. 33692
    Prev
    Next
    INDEX
    Explanations

    mathematical and code expressions

    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
    alap
    -0.08
    å®ĺæĸ¹åįļ客
    -0.07
    uba
    -0.07
    ifold
    -0.07
    orney
    -0.07
    åĨį说äºĨ
    -0.07
    queira
    -0.07
    <<<<<<<
    -0.07
    让广大
    -0.07
    _buffer
    -0.07
    POSITIVE LOGITS
     âĢ¦
    0.08
    åį´æ²¡æľī
    0.07
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.07
    æĹ¶è¡¨ç¤º
    0.07
    igt
    0.07
    âĢ¦
    0.07
    代表
    0.06
    æĮĩçļĦæĺ¯
    0.06
    sic
    0.06
    ’
    0.06
    Activations Density 0.002%

    No Known Activations