© 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. 23870
    Prev
    Next
    INDEX
    Explanations

    media and performance titles

    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
     previamente
    -0.08
    æ¬ł
    -0.08
    å½±è¦ĸ
    -0.07
    fér
    -0.06
    apons
    -0.06
    æĸĩç«łä¸Ń
    -0.06
    ä¾µ
    -0.06
     residing
    -0.06
    lander
    -0.06
     Movies
    -0.06
    POSITIVE LOGITS
    çĮ®ç»Ļ
    0.10
    主æŨ
    0.08
    éĹ®ä¸ĸ
    0.08
    æݢ讨äºĨ
    0.08
    åŁºè°ĥ
    0.08
     themes
    0.08
    æłĩé¢ĺ
    0.08
    åīįåįĬ
    0.08
    <|box_end|>
    0.08
    å¾Ī大ç¨ĭ度ä¸Ĭ
    0.08
    Activations Density 0.295%

    No Known Activations