© 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. 44391
    Prev
    Next
    INDEX
    Explanations

    can, could, should followed by verb

    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
     somehow
    -0.09
     unbedingt
    -0.08
    åı¯çľŁ
    -0.07
     assolutamente
    -0.07
     absolument
    -0.07
    åı¯ä¸įæĺ¯
    -0.07
    à¸ģะ
    -0.07
    ordes
    -0.06
    chn
    -0.06
    nitz
    -0.06
    POSITIVE LOGITS
     Ñģмело
    0.10
    大åı¯
    0.09
    æĶ¾å¿ĥçļĦ
    0.08
    _UNUSED
    0.08
    ’t
    0.08
    ull
    0.08
    't
    0.08
    æĶ¾å¿ĥ
    0.08
    othing
    0.08
    ´t
    0.07
    Activations Density 0.155%

    No Known Activations