© 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. 52125
    Prev
    Next
    INDEX
    Explanations

    mesh filter, type, source

    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
     punc
    -0.08
     Caro
    -0.08
    éķ¿çº¦
    -0.07
     "()
    -0.07
    essay
    -0.07
    isle
    -0.07
    ples
    -0.07
     abbr
    -0.07
    大éĢļ
    -0.07
    å¿įä½ı
    -0.07
    POSITIVE LOGITS
    æłı
    0.09
     calculated
    0.08
     specified
    0.08
    æĮĩå®ļ
    0.08
    æĮĩå®ļçļĦ
    0.08
    èĩªå®ļä¹ī
    0.08
     Physics
    0.08
    åĭ¾éĢī
    0.08
     calculation
    0.08
     automatically
    0.07
    Activations Density 0.038%

    No Known Activations