© 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. 27111
    Prev
    Next
    INDEX
    Explanations

    does, is, bring, fix, determined

    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
    缮æłĩä»»åĬ¡
    -0.08
    zat
    -0.07
    ents
    -0.07
    主æĦı
    -0.07
     reta
    -0.07
    INLINE
    -0.07
     ''),
    -0.07
    weed
    -0.06
    ityEngine
    -0.06
    heets
    -0.06
    POSITIVE LOGITS
     dabei
    0.09
     thereof
    0.09
     hierbei
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    åıĤä¸İåħ¶ä¸Ń
    0.07
    åľ¨åħ¶ä¸Ń
    0.07
     daarvan
    0.07
     melakukannya
    0.07
     hierfür
    0.07
    åħ¶ä¸ŃçļĦ
    0.07
    Activations Density 0.132%

    No Known Activations