© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8969
    Prev
    Next
    INDEX
    Explanations

    data stream originating

    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
    éĩijåĪ¸
    -0.08
    aszt
    -0.08
    áŀ¶áŀĽ
    -0.08
    alz
    -0.07
    pytest
    -0.07
    Fullscreen
    -0.07
    å®ĺæĸ¹å¾®ä¿¡
    -0.07
    atoi
    -0.07
    éĢ¼äºº
    -0.07
    ĥĿ
    -0.07
    POSITIVE LOGITS
    å½ĵåīį
    0.07
     configured
    0.07
     updates
    0.07
    åį³å°Ĩ
    0.07
    å½ĵåīįçļĦ
    0.07
     запÑĢа
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    份éĩı
    0.06
     processed
    0.06
    æŀģæľīåı¯èĥ½
    0.06
    Activations Density 0.003%

    No Known Activations