© 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. 54995
    Prev
    Next
    INDEX
    Explanations

    phase compensation

    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
    UNE
    -0.07
    etto
    -0.07
    èĬ¹
    -0.07
    unch
    -0.07
     اÙĦأط
    -0.07
    ogna
    -0.07
     Scal
    -0.07
    inp
    -0.06
    plaint
    -0.06
    ç½
    -0.06
    POSITIVE LOGITS
    ä»İèĢĮå½±åĵį
    0.08
    ä»İèĢĮ导èĩ´
    0.07
    æĹ¥çĶµ
    0.07
    woff
    0.07
    ä»İèĢĮ
    0.06
    æĹłåĩł
    0.06
    客
    0.06
    irá
    0.06
    æĹłç¼ĺ
    0.06
    æĥ®
    0.06
    Activations Density 0.022%

    No Known Activations