© 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. 56828
    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
    ething
    -0.07
    ä¼ĺç§Ģä½ľæĸĩ
    -0.07
    ä¸įçĦ¶
    -0.06
    çĤ¹åĩ»ä¸ĭè½½
    -0.06
    .cg
    -0.06
    å¦Ĥæŀľä¸įæĺ¯
    -0.06
    bracht
    -0.06
     gio
    -0.06
    inn
    -0.06
    odega
    -0.06
    POSITIVE LOGITS
    享
    0.07
    ä»Ģä¹Īåij¢
    0.07
    holm
    0.07
    upan
    0.07
    åħ¶èģĮ
    0.07
    uppy
    0.07
    ]|[
    0.07
     Maus
    0.07
    Īĺ
    0.06
     Nuova
    0.06
    Activations Density 0.000%

    No Known Activations