© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    LCD panel

    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
    èĩ
    -0.07
    è¯ļ
    -0.06
     outdoors
    -0.06
    วา
    -0.06
    ç¯
    -0.06
    isien
    -0.06
     TB
    -0.05
    å°ijèµ°
    -0.05
    大èĩªçĦ¶
    -0.05
     -
    -0.05
    POSITIVE LOGITS
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.08
    ียว
    0.08
    .googlecode
    0.08
    assi
    0.08
    lvl
    0.08
    oris
    0.08
    æŃ¤èµ·
    0.08
    åĬłåħ¥ä¹¦æŀ¶
    0.08
    urgi
    0.08
    MethodInfo
    0.08
    Activations Density 0.067%

    No Known Activations