© 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. 28209
    Prev
    Next
    INDEX
    Explanations

    back into or away from

    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
    ä¸Ģ鸣
    -0.09
    ycl
    -0.08
    人åij½
    -0.08
    ovin
    -0.08
     outright
    -0.08
    æĺİçģ«
    -0.08
    大çĤ®
    -0.07
     slog
    -0.07
    ÙĦاÙĥ
    -0.07
    моÑĤ
    -0.07
    POSITIVE LOGITS
     momentarily
    0.10
    èĻļå¹»
    0.09
    èĻļæĭŁ
    0.09
    çŁŃæļĤ
    0.09
    çŀ¬éĹ´
    0.09
    uspend
    0.08
     Via
    0.08
    å¢ĥçķĮ
    0.08
    æģįæĥļ
    0.08
     trasc
    0.08
    Activations Density 0.063%

    No Known Activations