© 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. 12379
    Prev
    Next
    INDEX
    Explanations

    connected and provide use

    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
    æĬĬèĩªå·±
    -0.08
    æĬĬå®ĥ
    -0.08
    æĬĬ人
    -0.07
    åľ¨å¤ĸéĿ¢
    -0.07
    æĬĬè¿Ļ个
    -0.07
    被åĪĹ为
    -0.07
    æĬĬä½ł
    -0.06
    æĬĬèĩªå·±çļĦ
    -0.06
    خذ
    -0.06
    å°Ĩåħ¶
    -0.06
    POSITIVE LOGITS
     Pue
    0.09
    à¹Ģà¸Ļืà¹īà¸Ńหาà¸Ĥà¸Ńà¸ĩ
    0.08
    enu
    0.08
    /]
    0.08
    icers
    0.08
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.08
    หà¸Ļึà¹Īà¸ĩà¸Ĥà¸Ńà¸ĩ
    0.07
    rors
    0.07
    ÙĴرÙIJ
    0.07
    rogen
    0.07
    Activations Density 0.243%

    No Known Activations