© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 3368
    Prev
    Next
    INDEX
    Explanations

    X-linked disorders

    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
    gaz
    -0.08
    OSP
    -0.08
    ап
    -0.08
    istring
    -0.08
     smar
    -0.08
    天éŃĶ
    -0.07
    æĿī
    -0.07
     ÙħÙĤد
    -0.07
    stroke
    -0.07
    _san
    -0.07
    POSITIVE LOGITS
     recess
    0.08
    åıijå±ķ模å¼ı
    0.08
    解éĩĬ
    0.07
    orter
    0.07
     involving
    0.07
     rarity
    0.07
    ç½ķè§ģçļĦ
    0.07
     explanatory
    0.07
     обÑĬÑıÑģ
    0.07
     explained
    0.07
    Activations Density 0.004%

    No Known Activations