© 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. 44325
    Prev
    Next
    INDEX
    Explanations

    explotab

    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
    请ä¸İæĪij们èģĶç³»
    -0.06
    ===============
    -0.06
    veal
    -0.06
    éĤĥ
    -0.05
    åī§æĥħä»ĭç»į
    -0.05
    sieme
    -0.05
    å·¡è§Ĩåijĺ
    -0.05
    erma
    -0.05
    aeda
    -0.05
    ivol
    -0.05
    POSITIVE LOGITS
    eneur
    0.08
    øl
    0.08
     prezi
    0.08
    yss
    0.07
    alang
    0.07
    øk
    0.07
    积çĶµ
    0.07
    å§Ķ书记
    0.07
    丽ä¸Ŀ
    0.07
    ablish
    0.07
    Activations Density 6.204%

    No Known Activations