© 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. 26242
    Prev
    Next
    INDEX
    Explanations

    readable, understandable, followable

    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
    ä¸Ģåİ»
    -0.08
     неÑĥ
    -0.08
    äch
    -0.08
    ä¸Ģå¤ķ
    -0.07
     Dw
    -0.07
    使å¾Ĺ
    -0.07
    hipster
    -0.07
    ä½ľçĶ¨æĺ¯
    -0.06
    ä½ķåħ¶
    -0.06
    ullets
    -0.06
    POSITIVE LOGITS
    åĴĮçIJĨ解
    0.10
    à¸ĩà¹Īาย
    0.09
    /read
    0.09
    æĺĵæĩĤ
    0.08
    белÑĮ
    0.08
    à¸ĩà¹Īายà¹Ĩ
    0.07
    æĺĵçĶ¨
    0.07
    à¸ĩà¹Īายà¸Ĥึà¹īà¸Ļ
    0.07
    able
    0.07
    zik
    0.07
    Activations Density 0.098%

    No Known Activations