© 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. 34977
    Prev
    Next
    INDEX
    Explanations

    frequency 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
    Negative Logits
    isan
    -0.08
     бÑİÑĢо
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    æݨ
    -0.07
    éĹ
    -0.07
    undry
    -0.07
    èķ
    -0.06
     arson
    -0.06
    æī«éĻ¤
    -0.06
     аÑĢми
    -0.06
    POSITIVE LOGITS
     transmitted
    0.10
     emitted
    0.10
     frequencies
    0.08
    èļĢ
    0.08
    ä¼łåĪ°
    0.08
     delivered
    0.07
    éĩĩ
    0.07
    ceived
    0.07
     exchanged
    0.07
    æľ¬åľ°
    0.07
    Activations Density 0.002%

    No Known Activations