© 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. 63546
    Prev
    Next
    INDEX
    Explanations

    the character Âł

    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
    æľĢæĸ°æĸĩç«ł
    -0.07
    häl
    -0.07
    ä¿ĿæĬ¤è£ħç½®
    -0.06
    ÑĩиÑĤа
    -0.06
    èĢĥè¯ķç½ij
    -0.06
    forme
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    æŀĹ家
    -0.06
    arts
    -0.06
    æĸ°è¿Ľ
    -0.06
    POSITIVE LOGITS
    VID
    0.07
     mũi
    0.06
    ross
    0.06
    ritel
    0.06
    cini
    0.06
    emain
    0.06
    æľĪæ´»åĬ¨
    0.06
    oto
    0.06
    ¤
    0.06
    ä¹İåħ¶
    0.06
    Activations Density 0.128%

    No Known Activations