© 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. 17889
    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
    ane
    -0.08
    ansk
    -0.06
    ADI
    -0.06
    cho
    -0.06
    udir
    -0.06
    åħ¶ä¸ŃåĮħæĭ¬
    -0.06
    æ¯ķç«Ł
    -0.06
    à´ķàµįà´·
    -0.06
    éĩij
    -0.06
    以
    -0.06
    POSITIVE LOGITS
    æ¯ı天æľī
    0.08
    LLU
    0.08
    å¾Ĺå¿ĥ
    0.08
    ä¸įç®¡ä½ł
    0.08
    æľī责任å¿ĥ
    0.08
    ebel
    0.08
    çĻ¾å®¶
    0.08
    ä¼ģä¸ļä¿¡æģ¯
    0.08
    æľī好çļĦ
    0.08
    atelj
    0.08
    Activations Density 0.000%

    No Known Activations