© 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. 4023
    Prev
    Next
    INDEX
    Explanations

    éĩİ ä¸īéĩį

    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
    ::*
    -0.07
    EXPORT
    -0.07
    çĥ
    -0.07
    æľīåħ³è´Łè´£äºº
    -0.07
    `.`
    -0.07
    éļıçĿĢæŶéĹ´çļĦæݨ移
    -0.07
    çĪĨäºĨ
    -0.07
    使çĶ¨å¯¿åij½éķ¿
    -0.07
    åIJĮ款
    -0.07
    ä¸į误
    -0.07
    POSITIVE LOGITS
    ä¸īéĩį
    0.07
    ÙĪÙĨÛĮ
    0.07
    éĩİ
    0.07
    unge
    0.07
     ë³´ëĭĪ
    0.07
    hare
    0.07
    åįģäºĮæĮĩ
    0.06
    ools
    0.06
    ำ
    0.06
    à¹Īà¸Ńà¸ĩ
    0.06
    Activations Density 0.002%

    No Known Activations