© 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. 57690
    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
    ors
    -0.07
    gio
    -0.07
    以便äºİ
    -0.07
    çľĭå¾Ĺè§ģ
    -0.07
    pton
    -0.07
    pris
    -0.07
     Fonseca
    -0.07
    orda
    -0.07
    roz
    -0.06
    fec
    -0.06
    POSITIVE LOGITS
    ynn
    0.08
    èķĥ
    0.07
    æİ¥ä¸ĭ
    0.07
     Haram
    0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.07
    ç¨ĭå¼ı
    0.07
    ilog
    0.07
    ANGLE
    0.07
    客æĪ·æıIJä¾Ľ
    0.06
    çī¹åĮº
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.