© 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. 52117
    Prev
    Next
    INDEX
    Explanations

    general equations or lines

    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
    å¦Ĥæŀľä»ĸ们
    -0.08
    ertools
    -0.08
    umbs
    -0.08
    quare
    -0.08
    Æł
    -0.08
    elai
    -0.08
    å¦Ĥä»ĬçļĦ
    -0.08
    arang
    -0.08
    åIJ¯äºĭ
    -0.08
     Baju
    -0.08
    POSITIVE LOGITS
    oke
    0.07
    éķ¿æľŁä½¿çĶ¨
    0.06
    inkel
    0.06
    令
    0.06
    fir
    0.06
     gerade
    0.06
    ink
    0.06
    è¡Į驶æŶ
    0.06
     choked
    0.06
    kit
    0.06
    Activations Density 0.005%

    No Known Activations