© 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. 42351
    Prev
    Next
    INDEX
    Explanations

    represent or reflect

    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
    initializer
    -0.09
     dringend
    -0.08
    RIA
    -0.08
    .generated
    -0.08
    orida
    -0.08
     cra
    -0.08
    ÑĤÑĢе
    -0.07
    OBO
    -0.07
    æľīäºĶ
    -0.07
    æľīä¸Ģ家
    -0.07
    POSITIVE LOGITS
    åıįæĺł
    0.10
    ä»ħ代表
    0.10
     reflects
    0.10
    åıįæĺłäºĨ
    0.09
     reflect
    0.09
    åıªä»£è¡¨
    0.09
    羣å®ŀçļĦ
    0.09
     represent
    0.08
     true
    0.08
    çŁŃæŶéĹ´
    0.08
    Activations Density 0.072%

    No Known Activations