© 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. 55394
    Prev
    Next
    INDEX
    Explanations

    become or becomes

    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
     бÑĭваеÑĤ
    -0.08
    ``
    -0.07
    eding
    -0.07
    ä¾Ŀæ³ķ追究责任
    -0.07
    ieger
    -0.07
    åī¯æĢ»è£ģ
    -0.07
    anes
    -0.07
    smith
    -0.07
    uten
    -0.06
    æĺ¯å¦ĤæѤ
    -0.06
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.09
    ï¼ļ
    0.08
    fter
    0.08
    :
    0.08
    æľīäºĨ
    0.08
    mehr
    0.07
    å¦Ĥä¸ĭ
    0.07
    icamente
    0.07
    ________________________________________________________________
    0.06
    wel
    0.06
    Activations Density 0.005%

    No Known Activations