© 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. 58596
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    ly
    -0.19
    er
    -0.11
    raries
    -0.11
    iele
    -0.10
    اÙĭ
    -0.09
    erio
    -0.09
    ر
    -0.09
    erate
    -0.09
    eret
    -0.09
    erie
    -0.09
    POSITIVE LOGITS
    åĻľ
    0.08
    indow
    0.08
    য়à§ĩর
    0.07
    пÑĢинима
    0.07
    schaften
    0.06
    ä»ħä»£è¡¨ä½ľèĢħ
    0.06
    ÑİÑīиÑħ
    0.06
    chia
    0.06
    bach
    0.06
    çĽ¸ä¼¼æĸĩçĮ®
    0.06
    Activations Density 0.008%

    No Known Activations