© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50248
    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
    enarios
    -0.07
    Follow
    -0.07
    olog
    -0.07
    ä½łä¸Ģ个
    -0.07
    _both
    -0.07
    -follow
    -0.07
    önen
    -0.07
    çī©ç¾İ
    -0.07
     Follow
    -0.07
    ças
    -0.07
    POSITIVE LOGITS
    èµĽ
    0.07
    KD
    0.06
    <\/
    0.06
    åħ¬åŃIJ
    0.06
    excel
    0.06
     PROGMEM
    0.06
    ÙģØ´
    0.06
     Walton
    0.06
    ä¸ĢåŃĹ
    0.06
    æıIJé«ĺèĩªèº«
    0.06
    Activations Density 0.000%

    No Known Activations