© 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. 15243
    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
    pit
    -0.07
    è¤
    -0.07
    çī
    -0.07
    áĥĺáĥ¢
    -0.07
    æģ¯æģ¯
    -0.06
    æ¶Ī
    -0.06
     Mason
    -0.06
    ashian
    -0.06
    è¯Ħä»·ä½ĵç³»
    -0.06
    çIJĨåıij
    -0.06
    POSITIVE LOGITS
    éķĤ
    0.07
    æĿ¥å®¾
    0.07
    èijĨ
    0.07
    åĴĸ
    0.07
    åģļå·¥
    0.07
    enga
    0.07
     internals
    0.07
    erti
    0.07
    åģļåĩºçļĦ
    0.07
    retti
    0.07
    Activations Density 0.000%

    No Known Activations