© 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. 9133
    Prev
    Next
    INDEX
    Explanations

    electronic devices, food, and places

    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
     roughly
    -0.08
    å¦Ĥæ°´
    -0.08
    è¨Ģä¹ĭ
    -0.08
    大æ¦Ĥ
    -0.07
     essentially
    -0.07
    ØŃدة
    -0.07
     presumably
    -0.07
    åıĬåħ¶å®ĥ
    -0.06
    uisse
    -0.06
    绿水
    -0.06
    POSITIVE LOGITS
     denen
    0.10
     appunto
    0.09
    noz
    0.08
    AWN
    0.08
    ÙĨÙĪ
    0.08
    çŃīè¿Ľè¡Į
    0.08
    å°±æĽ¾
    0.07
    ãģĸãģ¾
    0.07
    ahr
    0.07
     à¹Ģà¸Ľà¹ĩà¸Ļà¸ķà¹īà¸Ļ
    0.07
    Activations Density 0.385%

    No Known Activations