© 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. 31627
    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
    夫妻æĦŁæĥħ
    -0.08
    ihak
    -0.07
    ultas
    -0.07
    icana
    -0.07
    /*/
    -0.07
    èĢĮåĸ»
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.07
    plant
    -0.07
    åĬ¿åľ¨å¿ħ
    -0.07
    hende
    -0.07
    POSITIVE LOGITS
    ÙİÙĬÙĴÙĨ
    0.07
    æĶ¶æķĽ
    0.07
    ç§ī
    0.07
     famously
    0.06
    è¡
    0.06
    å¡ļ
    0.06
    á»Ļ
    0.06
    jev
    0.06
    enton
    0.06
    è¨ĺ
    0.06
    Activations Density 0.000%

    No Known Activations