© 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. 16525
    Prev
    Next
    INDEX
    Explanations

    Irish names or terms

    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
    무를
    -0.07
    ertz
    -0.07
    .alt
    -0.07
    hun
    -0.06
    ç¢į
    -0.06
     shall
    -0.06
    evol
    -0.06
    adra
    -0.06
    并就
    -0.06
    è¯ģå®ŀåħ¶
    -0.06
    POSITIVE LOGITS
    æŁIJäºĽ
    0.10
    åľ¨æŁIJäºĽ
    0.09
     Certain
    0.09
    æľīè¿Ļæł·
    0.09
    æľīä¸Ģç§į
    0.08
    常æľī
    0.08
    æŁIJç§į
    0.08
    Certain
    0.08
     certain
    0.08
    vand
    0.07
    Activations Density 0.039%

    No Known Activations