© 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. 46366
    Prev
    Next
    INDEX
    Explanations

    long articles and details

    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
    ç®Ģåįķæĺĵ
    -0.09
    andi
    -0.08
    å¾Īç®Ģåįķ
    -0.08
     simplicity
    -0.08
    ccio
    -0.08
    ç»ĵæŀĦç®Ģåįķ
    -0.08
    æľĢç®Ģåįķ
    -0.08
    å¿«éĢŁèİ·åıĸ
    -0.08
    å¹²åĩĢ
    -0.08
    oho
    -0.08
    POSITIVE LOGITS
     detailed
    0.10
    详ç»Ĩ
    0.09
     detail
    0.09
     подÑĢоб
    0.09
    详ç»ĨçļĦ
    0.09
    ç»ĨèĬĤ
    0.09
     Detail
    0.09
     detailing
    0.08
    ç»Ĩèĩ´
    0.08
    足足
    0.08
    Activations Density 0.043%

    No Known Activations