© 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. 56119
    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
    sted
    -0.09
     Lees
    -0.07
     Lion
    -0.07
    -ahead
    -0.07
     recul
    -0.07
    igen
    -0.07
    .gstatic
    -0.07
    cona
    -0.07
    are
    -0.07
    rek
    -0.07
    POSITIVE LOGITS
    è¯ģæĺİ
    0.10
    æļĩ
    0.09
    èŃīæĺİ
    0.09
     proving
    0.08
     proof
    0.08
    è¯ģæį®è¯ģæĺİ
    0.07
    ildo
    0.07
    uthor
    0.07
     prove
    0.07
     proves
    0.07
    Activations Density 0.000%

    No Known Activations