© 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. 51871
    Prev
    Next
    INDEX
    Explanations

    CP and T violation

    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
     Yad
    -0.08
    aczy
    -0.08
    yfik
    -0.07
    åĢĻéĢī
    -0.07
    abad
    -0.07
    estal
    -0.07
     Candidate
    -0.07
    åĴĮè§Ĩé¢ij
    -0.07
    fox
    -0.07
    åĢĻéĢī人
    -0.07
    POSITIVE LOGITS
    æ¤į
    0.08
    scher
    0.07
    夹è§Ĵ
    0.07
    è§Ĵ
    0.07
     angle
    0.07
    (angle
    0.07
    åŃ½
    0.07
    iedad
    0.07
    èĤļçļ®
    0.07
    umbu
    0.07
    Activations Density 0.002%

    No Known Activations