© 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. 38456
    Prev
    Next
    INDEX
    Explanations

    reproduced original text

    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
    æŁ¥æŁ¥
    -0.08
    ợi
    -0.08
    两çĶ¨
    -0.08
    estand
    -0.08
    chien
    -0.08
    bien
    -0.08
    妨害
    -0.07
    å¥ĭ
    -0.07
    бак
    -0.07
    иÑĤо
    -0.07
    POSITIVE LOGITS
    åİŁæĸĩ
    0.15
     original
    0.15
    åİŁæ±ģ
    0.14
     ê·¸ëĮĢë¡ľ
    0.14
    original
    0.13
    åİŁ
    0.13
    Original
    0.12
    ãģĿãģ®ãģ¾ãģ¾
    0.12
     Original
    0.12
    åİŁå§ĭ
    0.12
    Activations Density 0.163%

    No Known Activations