© 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. 41739
    Prev
    Next
    INDEX
    Explanations

    humanitarian crises and displacement

    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
    为顾客
    -0.07
    unicorn
    -0.07
     cocks
    -0.07
    ç¥Ń
    -0.07
    è¢«æŁ¥
    -0.06
     Senato
    -0.06
     Saudis
    -0.06
    NST
    -0.06
    顾客
    -0.06
    åİī
    -0.06
    POSITIVE LOGITS
     humanitarian
    0.13
    人æĿĥ
    0.11
    çŃīåĽ½éĻħ
    0.10
    人éģĵ
    0.10
    红åįģåŃĹ
    0.09
    peace
    0.09
    å±ĢåĬ¿
    0.09
    éļ¾æ°ij
    0.09
     ÐŀÐŀÐĿ
    0.09
    èģĶåIJĪåĽ½
    0.09
    Activations Density 0.176%

    No Known Activations