© 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. 8436
    Prev
    Next
    INDEX
    Explanations

    asking because

    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
    remo
    -0.07
    cez
    -0.07
    è¯Ħ论åĨħ容
    -0.07
    彷徨
    -0.07
    ä»Ģä¹Īåı«
    -0.06
     Keb
    -0.06
    çļĦæĪij
    -0.06
    osg
    -0.06
    æĺ¯ä»Ģä¹Īæł·çļĦ
    -0.06
    èIJ©
    -0.06
    POSITIVE LOGITS
    æĺ¯åĽłä¸º
    0.26
    ä¹ĭæīĢ以
    0.23
     because
    0.22
    æĺ¯åĽłçĤº
    0.21
    because
    0.21
    主è¦ģæĺ¯åĽłä¸º
    0.19
     porque
    0.19
     поÑĤомÑĥ
    0.18
    åĽłä¸º
    0.18
    åĽłä¸ºåľ¨
    0.18
    Activations Density 0.362%

    No Known Activations