© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    html table tags or code structures

    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
    éļĪ
    -0.07
    ime
    -0.07
    pan
    -0.06
    quir
    -0.06
    åľ¨ä½ł
    -0.06
    _LIBRARY
    -0.06
    æį§
    -0.06
     pare
    -0.06
    å¯ħ
    -0.06
    ä¹ĥ
    -0.06
    POSITIVE LOGITS
    æľīæĿ¡ä»¶çļĦ
    0.08
    kek
    0.07
    ä¿¡æģ¯åıĬ
    0.07
    å·²åĪ°
    0.07
    çĶŁæ´»åŀĥåľ¾
    0.07
    ãĤµãĥ¼
    0.07
     Neighbor
    0.07
    èµıæľĪ
    0.07
    agine
    0.07
    REST
    0.07
    Activations Density 0.023%

    No Known Activations