© 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. 10378
    Prev
    Next
    INDEX
    Explanations

    adjectives describing conditions, qualities, or states

    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
     protester
    -0.08
    ä¼¼çļĦ
    -0.08
    ences
    -0.08
    Ñĩи
    -0.08
    hangi
    -0.08
    обÑĢазие
    -0.08
    åijĹ
    -0.07
    çļĦ人æĺ¯
    -0.07
    æĸĩåĮĸåĨħ涵
    -0.07
    undos
    -0.07
    POSITIVE LOGITS
    ãĤĤãģ®ãģ§ãģĤãĤĭ
    0.10
    çļĦä¸Ģåijĺ
    0.09
    åIJįåī¯åħ¶å®ŀçļĦ
    0.08
    çļĦä¸Ģéĥ¨åĪĨ
    0.08
    ä¸Ķ
    0.07
    éĢļè¿ĩæŃ¤æ¬¡
    0.07
     Bestandteil
    0.07
     consequence
    0.07
    Scrollbar
    0.07
    åĽłä¸ºå®ĥ
    0.07
    Activations Density 0.248%

    No Known Activations