© 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. 59015
    Prev
    Next
    INDEX
    Explanations

    shielding effect, wall, humans, radio

    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
    .au
    -0.07
    سÙĬس
    -0.07
    åIJijèį£
    -0.07
    curring
    -0.07
    spre
    -0.07
    plet
    -0.07
    士æŀĹ
    -0.07
    ë§ĪìŀIJ
    -0.07
     неÑģко
    -0.07
    upon
    -0.06
    POSITIVE LOGITS
    ä¸į严
    0.10
    ä¸įä½ıçļĦ
    0.10
    å¾Ĺä½ı
    0.09
    èĶ½
    0.09
    æķĪåºĶ
    0.09
    abras
    0.09
    ä½ij
    0.08
    ä¸įä½ıäºĨ
    0.08
    wirkung
    0.08
    edly
    0.08
    Activations Density 0.015%

    No Known Activations