© 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. 48759
    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
    лежа
    -0.08
    lef
    -0.08
    æ¼ĵ
    -0.07
     goog
    -0.07
    åĴĮæľīåħ³
    -0.07
    lima
    -0.07
    lix
    -0.07
    hyl
    -0.07
    çŃīæľīåħ³
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    POSITIVE LOGITS
    _attachments
    0.07
     att
    0.07
    atrix
    0.07
    æĹłå¿§
    0.06
     Patch
    0.06
    ators
    0.06
    祥åĴĮ
    0.06
     Authority
    0.06
    atori
    0.06
    éĢĿ
    0.06
    Activations Density 0.000%

    No Known Activations