© 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. 25591
    Prev
    Next
    INDEX
    Explanations

    mobile cellular devices geographical

    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
    -0.09
    秫
    -0.08
    èĺĭ
    -0.07
     vorig
    -0.07
    ç®
    -0.07
    æª
    -0.07
    моÑĤ
    -0.07
    è¿Ń
    -0.07
    ãĥ¼ãĥĹ
    -0.07
     unsuccessfully
    -0.07
    POSITIVE LOGITS
    .xx
    0.08
    charg
    0.08
    ä¸ĢåĪ»
    0.07
    æĪijåĸľæ¬¢
    0.07
    åij¨å²ģçļĦ
    0.07
    人åĸľæ¬¢
    0.07
     Horr
    0.06
    å®ļä¹ī为
    0.06
    chten
    0.06
    each
    0.06
    Activations Density 0.016%

    No Known Activations