© 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. 55270
    Prev
    Next
    INDEX
    Explanations

    sudden changes or reversals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    代代
    -0.08
    egah
    -0.07
    ç´¢æĢ§
    -0.07
    оÑĤоÑĢ
    -0.07
     accr
    -0.07
    å¾Ĺ天çĭ¬
    -0.06
    æľī人ä¼ļ
    -0.06
    篡
    -0.06
    注å®ļ
    -0.06
     landet
    -0.06
    POSITIVE LOGITS
     suddenly
    0.12
    ä¸įåĨį
    0.11
     plötzlich
    0.11
    çªģçĦ¶
    0.11
    ä¸ĢæĶ¹
    0.10
    uddenly
    0.10
    转åıĺ
    0.10
    ä¸Ģåıį
    0.10
     repente
    0.09
     внезапно
    0.09
    Activations Density 0.327%

    No Known Activations