© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33243
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes

    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
    ä½ķåİ»ä½ķ
    -0.09
    erner
    -0.09
    à¹ģà¸¥à¸°à¸ľà¸¹à¹ī
    -0.09
    yiz
    -0.09
    åĴĮä¼ģä¸ļ
    -0.09
    åĽłåľ°
    -0.09
    精彩åĨħ容
    -0.09
    çļĦ精彩
    -0.09
    ä¹ĭä¸ĢçļĦ
    -0.09
    åĴĮ产åĵģ
    -0.09
    POSITIVE LOGITS
    ç¨ĭ度
    0.12
    ly
    0.09
    ness
    0.09
    ä¹ĭå¤Ħ
    0.09
    èĢĮ
    0.09
    èĩ³æŀģ
    0.09
    èĢĮåıĪ
    0.09
    ä¸Ķ
    0.09
     enough
    0.09
    ãĢģ
    0.09
    Activations Density 0.005%

    No Known Activations