© 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. 24750
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    çĥŃéŨæIJľç´¢
    -0.07
    åģļèµ·
    -0.07
    à¸ģลาà¸ĩ
    -0.07
    æĹłèĥ½
    -0.07
    kler
    -0.07
     ausgeb
    -0.07
    éĤ£æĺ¯åĽłä¸º
    -0.06
    idio
    -0.06
     fronti
    -0.06
    ibs
    -0.06
    POSITIVE LOGITS
     tehát
    0.09
    åĺĽ
    0.08
     donc
    0.08
    ä¹Łç¡®å®ŀ
    0.07
    ãģĹãģ¾ãģĻãģ®ãģ§
    0.07
    _>
    0.07
    ãģ§ãģĻãģĭãĤī
    0.07
     übrigens
    0.07
     ведÑĮ
    0.07
     therefore
    0.07
    Activations Density 0.024%

    No Known Activations