© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34812
    Prev
    Next
    INDEX
    Explanations

    vitamin, chapter, type, CD, level, font

    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
    Negative Logits
    éĤ£ä¹Īåľ¨
    -0.08
    çĨ¬
    -0.07
    atism
    -0.06
    θα
    -0.06
    cci
    -0.06
    enius
    -0.06
    kets
    -0.06
    åĩłåı¥è¯Ŀ
    -0.06
    åı¯å¾ª
    -0.06
     enjo
    -0.06
    POSITIVE LOGITS
    eway
    0.07
    esta
    0.07
    ®
    0.07
    è¿Ļéĥ¨åĪĨ
    0.07
    aped
    0.07
    è¥Ħ
    0.07
    rus
    0.07
    å¾Ĺåħ¶
    0.07
     обно
    0.07
    该类
    0.06
    Activations Density 0.026%

    No Known Activations