© 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. 3583
    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
    夫æĸ¯åŁº
    -0.08
    ç½ijç«Ļåľ°åĽ¾
    -0.08
    æĩĤ
    -0.08
    unci
    -0.08
    ষà§į
    -0.07
    GENCY
    -0.07
    uning
    -0.07
    unica
    -0.07
    ewe
    -0.07
     Mesin
    -0.07
    POSITIVE LOGITS
    å²
    0.07
    Âł
    0.06
    amps
    0.06
    eldorf
    0.06
    orian
    0.06
    æŀĦæĪIJ
    0.06
    天涯
    0.06
    æŀĹç«ĭ
    0.06
    æľĢå¤ļçļĦ
    0.06
    .oracle
    0.06
    Activations Density 0.000%

    No Known Activations