© 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. 42759
    Prev
    Next
    INDEX
    Explanations

    creating value and establishing

    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
    åĽłä¸º
    -0.07
    æľīä¸Ģå®ļçļĦ
    -0.07
    åĽłä¸ºåħ¶
    -0.07
    äºĨ解ä¸Ģä¸ĭ
    -0.06
    ок
    -0.06
    æĹ©çĤ¹
    -0.06
     Morg
    -0.06
    æľīä¸Ģå®ļ
    -0.06
    äºĨ解ä¸ĭ
    -0.06
    åĽłåħ¶
    -0.06
    POSITIVE LOGITS
    æľĢç»Ī以
    0.10
    è¿Ļæīįæĺ¯
    0.09
     ultimately
    0.09
    ä»İèĢĮè¾¾åĪ°
    0.09
    æĢ»ç½²
    0.08
    æľĢç»ĪçļĦ
    0.08
    jaw
    0.08
     letztlich
    0.08
    ç»Īäºİåľ¨
    0.08
    pios
    0.08
    Activations Density 0.012%

    No Known Activations