© 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. 34755
    Prev
    Next
    INDEX
    Explanations

    phase shift

    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
     possibil
    -0.07
     Ore
    -0.07
    纵深
    -0.07
    andes
    -0.07
    .gdx
    -0.07
    ä»»çĶ±
    -0.06
    æľĹæľĹ
    -0.06
    èĩªçĦ¶æĺ¯
    -0.06
    éĹŃ
    -0.06
    bes
    -0.06
    POSITIVE LOGITS
     reversal
    0.08
     inversion
    0.08
     accounted
    0.07
    apis
    0.07
    itus
    0.07
     flips
    0.07
    apse
    0.07
    é¡¹çĽ®æī¿åĬŀåįķä½į
    0.07
     polarity
    0.07
    åIJ¦
    0.07
    Activations Density 0.001%

    No Known Activations