© 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. 63906
    Prev
    Next
    INDEX
    Explanations

    sequence markers

    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
    urt
    -0.07
    足足
    -0.07
    ehme
    -0.07
     (()
    -0.07
    æķĻäºİ
    -0.07
    occo
    -0.07
    åħĨ
    -0.07
    /front
    -0.06
    起家
    -0.06
    æĶ¹æŃ£
    -0.06
    POSITIVE LOGITS
    ä¸ĢçļĦ
    0.12
    หà¸Ļึà¹Īà¸ĩ
    0.10
    à¹ģรà¸ģ
    0.10
    âij
    0.09
    หà¸Ļึà¹Īà¸ĩà¸Ĺีà¹Ī
    0.09
    âĤģ
    0.09
     pertama
    0.09
     اÙĦØ£ÙĪÙĦ
    0.08
    äºĮçļĦ
    0.08
    ä¹ĭä¸Ģæĺ¯
    0.08
    Activations Density 0.063%

    No Known Activations