© 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. 44712
    Prev
    Next
    INDEX
    Explanations

    concentrate or concentration

    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
    à¹Ģà¸Ħียà¸ĩ
    -0.08
    atsby
    -0.08
    etting
    -0.08
    éģįäºĨ
    -0.08
    -long
    -0.07
    affer
    -0.07
    åħ¬åħģ
    -0.07
    èģĶè¿IJ
    -0.07
    à¹ģà¸ģà¹Ī
    -0.07
     aloud
    -0.07
    POSITIVE LOGITS
    éĽĨä¸Ń
    0.14
    éĽĨä¸ŃçļĦ
    0.14
    éĽĨä¸Ńåľ¨
    0.13
     concentrated
    0.13
     concentrate
    0.11
    èģļéĽĨ
    0.11
    ä¸įæķ£
    0.11
     Concent
    0.11
     concentration
    0.11
     concentrating
    0.11
    Activations Density 0.056%

    No Known Activations