© 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. 47789
    Prev
    Next
    INDEX
    Explanations

    percent or percentage

    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
    elan
    -0.08
    rano
    -0.08
    dan
    -0.07
    ont
    -0.07
    inet
    -0.07
    ÑĪÑĤо
    -0.07
    iens
    -0.07
     bá»ķ
    -0.07
    æī£
    -0.06
    ãĤ¬ãĤ¤
    -0.06
    POSITIVE LOGITS
    举é£İ
    0.07
    avar
    0.07
    æµ®çĶŁ
    0.07
    缼äºĭ
    0.07
     Coppa
    0.07
    æĸ¯åŁº
    0.07
    çĶŁçļĦ
    0.07
    armi
    0.07
    äºİäºĭ
    0.07
    usercontent
    0.07
    Activations Density 0.017%

    No Known Activations