© 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. 12174
    Prev
    Next
    INDEX
    Explanations

    architectural features, push back, move it

    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
     ðŁĺ
    -0.06
    çĸĹåħ»
    -0.06
    åĬłæĸ¯
    -0.06
    åĨ°å±±
    -0.06
    -validator
    -0.06
     âĿ¤
    -0.06
     “
    -0.06
     *
    -0.06
    \base
    -0.05
    åį°æŁĵ
    -0.05
    POSITIVE LOGITS
    ä¸¥æł¼æĮīçħ§
    0.10
    åıĬè¦ģæ±Ĥ
    0.09
    æĿIJæĸĻåıĬ
    0.09
    ä¸¥æł¼æĮī
    0.09
     McDon
    0.09
    æ¯ıçıŃ
    0.09
    çĶ±ä¹Ļæĸ¹
    0.08
    åĨħ容åıĬ
    0.08
    åĿĩçĶ±
    0.08
    åĿĩéĩĩçĶ¨
    0.08
    Activations Density 0.001%

    No Known Activations