© 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. 18034
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ·³
    -0.08
    æį·
    -0.07
    æģ¶æĢ§
    -0.07
    á»ĵng
    -0.07
    ä¸ĥ大
    -0.07
    åĢ¼å¾Ĺä¸Ģ
    -0.06
    lick
    -0.06
     semula
    -0.06
    åīĬ
    -0.06
     Elliott
    -0.06
    POSITIVE LOGITS
     Dus
    0.09
    .fm
    0.08
    etag
    0.07
    agus
    0.07
    大湾åĮº
    0.07
    žil
    0.07
    æĹłæķ°çļĦ
    0.07
    гам
    0.06
     ván
    0.06
    æ£ł
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.