© 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. 7581
    Prev
    Next
    INDEX
    Explanations

    reverse engineering

    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
     equally
    -0.07
    èĶļ
    -0.07
    èĥĮéĿ¢
    -0.07
    è¿ijçĻ¾
    -0.06
    chter
    -0.06
    weich
    -0.06
    adoo
    -0.06
    欲
    -0.06
    èĥĮ
    -0.06
    jep
    -0.06
    POSITIVE LOGITS
    åİŁæľīçļĦ
    0.13
    Previously
    0.12
     пÑĢеж
    0.12
     previously
    0.12
    åİŁåħĪ
    0.11
    åİŁæĿ¥
    0.11
     ÑĢанее
    0.11
    继ç»Ńåħ³æ³¨
    0.10
    à¹Ģà¸Ķิม
    0.10
    åİŁæĿ¥çļĦ
    0.10
    Activations Density 0.944%

    No Known Activations