© 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. 10468
    Prev
    Next
    INDEX
    Explanations

    names and initial identifiers

    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
    ï¾ŀ
    -0.07
    ocaust
    -0.07
    ä¸ĢæĬ¹
    -0.06
    èĢģé¹°
    -0.06
    æ²®
    -0.06
    egar
    -0.06
    çļĦæŶåĢĻåı¯ä»¥
    -0.06
    ÙĥÙIJ
    -0.06
    æĺ¯å¤ļå°ij
    -0.06
    iber
    -0.06
    POSITIVE LOGITS
    ä¿¡æģ¯çĶ±
    0.07
    ,proto
    0.07
    æĿijæĿijæ°ij
    0.07
    æĺ¯ä¸ĢåIJį
    0.07
    åĴĮäºĮ
    0.07
    eté
    0.07
    ples
    0.07
    onta
    0.07
    ·
    0.07
    noinspection
    0.07
    Activations Density 0.015%

    No Known Activations