© 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. 29246
    Prev
    Next
    INDEX
    Explanations

    cellular telephone

    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
    ilog
    -0.08
    ÏĨÏħ
    -0.07
     lÃŃ
    -0.07
    以å¾ĢçļĦ
    -0.07
    æª
    -0.07
     beforehand
    -0.07
    请注æĺİ
    -0.07
    çļĦéĤ£ä¸Ģ天
    -0.07
    äºĮè¦ģ
    -0.06
     пÑĢедваÑĢиÑĤелÑĮно
    -0.06
    POSITIVE LOGITS
    åı¯è°ĵ
    0.07
    Say
    0.07
    西åİ¿
    0.07
    aken
    0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    0.07
    JNI
    0.07
     redak
    0.06
    alen
    0.06
    Den
    0.06
    rowse
    0.06
    Activations Density 0.025%

    No Known Activations