© 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. 39830
    Prev
    Next
    INDEX
    Explanations

    lightning

    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
    æ¢ħæŀĹ
    -0.08
    人æĿ¥
    -0.07
    wayne
    -0.07
    iy
    -0.07
    bolt
    -0.06
    acock
    -0.06
    åħĪçĶŁçļĦ
    -0.06
    acu
    -0.06
    enberg
    -0.06
    æľ¬æ¬¡ä¼ļè®®
    -0.06
    POSITIVE LOGITS
    lát
    0.08
    åĿ¦
    0.07
    epy
    0.07
    зи
    0.07
    æŃ¢
    0.07
    åĵį
    0.06
    Ñģпа
    0.06
    å»ĵ
    0.06
    èIJ½äºĨ
    0.06
    æ²¥
    0.06
    Activations Density 0.349%

    No Known Activations