© 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. 61520
    Prev
    Next
    INDEX
    Explanations

    names of places or people

    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
    urgeon
    -0.07
    må
    -0.07
    ÐłÐ¾
    -0.07
    (Char
    -0.06
    æĢİä¹ĪåĬŀåij¢
    -0.06
    Ðĵо
    -0.06
    çŃīä¸ĢäºĽ
    -0.06
    _POINT
    -0.06
    cle
    -0.06
    æľ¬èº«
    -0.06
    POSITIVE LOGITS
     appunto
    0.11
    ä¹ŁæŃ£æĺ¯
    0.09
    第ä¸īèĢħ
    0.07
     ÐŁÑĢавда
    0.07
    ierz
    0.07
    æŀľçĦ¶æĺ¯
    0.07
    åĮ»åѦè§Ĥå¯Ł
    0.07
    ÙĬÙĦÙĩ
    0.07
    interes
    0.07
     кÑģÑĤаÑĤи
    0.07
    Activations Density 0.012%

    No Known Activations