© 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. 63000
    Prev
    Next
    INDEX
    Explanations

    male and female

    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
    onar
    -0.08
    ãģ°ãģĭãĤĬ
    -0.07
    оÑĢа
    -0.07
    sey
    -0.07
     Entire
    -0.06
    åħ¨éĿ¢äºĨ解
    -0.06
    åħ¨ç¨ĭ
    -0.06
    agle
    -0.06
    ä¸įä½Ĩ
    -0.06
    综åIJĪèĢĥèĻij
    -0.06
    POSITIVE LOGITS
     تÙĤرÙĬب
    0.10
    åĮºåĪ«
    0.08
    è°ģéĥ½
    0.08
    wehr
    0.08
    éĥ½ä¼ļæľī
    0.08
    sker
    0.08
    éĥ½ä¸Ģæł·
    0.08
    éĥ½ä¼ļ
    0.08
    éĥ½åı¯ä»¥
    0.08
    éĥ½éľĢè¦ģ
    0.08
    Activations Density 0.130%

    No Known Activations