© 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. 48604
    Prev
    Next
    INDEX
    Explanations

    possibility of occurrence

    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
    ذاÙĥ
    -0.08
    abad
    -0.08
    ught
    -0.07
    stum
    -0.07
    =-=-=-=-=-=-=-=-
    -0.07
    usercontent
    -0.07
    æĺ¯ä½ķåIJ«ä¹ī
    -0.07
    ç¼Ī
    -0.07
     others
    -0.07
    äºİæĺ¯ä»ĸ
    -0.07
    POSITIVE LOGITS
    -profile
    0.06
    è§ģè¯Ĩ
    0.06
    èªŀ
    0.06
    orre
    0.06
    ãĤĢãģĹãĤį
    0.06
    asser
    0.06
    æĢ§æĺ¯
    0.06
    ServerError
    0.06
     phenomenon
    0.06
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations