© 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. 62833
    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
    orer
    -0.08
    ç»ĪçĶŁ
    -0.06
    æĬ¼
    -0.06
    apor
    -0.06
    ä¸ĵ
    -0.06
    温çĥŃ
    -0.06
     hei
    -0.06
    rna
    -0.06
    plast
    -0.06
    iby
    -0.06
    POSITIVE LOGITS
     Raw
    0.08
    inine
    0.07
    aub
    0.07
    责任æĦıè¯Ĩ
    0.07
     demonstrating
    0.07
     setC
    0.07
    _STRUCTURE
    0.07
    åµ
    0.07
    asley
    0.07
    æĥ³çĿĢ
    0.07
    Activations Density 0.000%

    No Known Activations