© 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. 2883
    Prev
    Next
    INDEX
    Explanations

    list item separator

    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
    à¸¹à¸Ľ
    -0.07
    éľĢè¦ģä¸Ģ个
    -0.07
    ä¸įèĥ½çĶ¨
    -0.07
    åı¯èĥ½è¦ģ
    -0.07
    éĢļ常éľĢè¦ģ
    -0.07
    åı¯èĥ½éľĢè¦ģ
    -0.07
    ä¸Ĭä¸Ģç¯ĩ
    -0.07
    æĸ¹å¼ıæĿ¥
    -0.06
    Č↵
    -0.06
    ectl
    -0.06
    POSITIVE LOGITS
    éĵ¶æ²³
    0.07
    设å¤ĩåĪ¶éĢł
    0.07
    æĹ
    0.07
    cean
    0.06
    l
    0.06
    ÑĦелÑĮ
    0.06
    åı¥åı¥
    0.06
    aed
    0.06
     prepared
    0.06
    éb
    0.06
    Activations Density 0.002%

    No Known Activations