© 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. 10807
    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
    еÑĩ
    -0.07
    inson
    -0.07
    æķĻèģĮ
    -0.07
    ä¸Ģé¢Ĺ
    -0.07
    æīĢåľ¨åľ°åĮº
    -0.07
    ovah
    -0.07
    ream
    -0.07
    ä¸Ģç±»
    -0.07
    ä¸Ģåıij
    -0.07
    ivers
    -0.07
    POSITIVE LOGITS
    ãĥĥãĤŃ
    0.07
    cky
    0.07
    ÑĨени
    0.07
     explo
    0.06
     exploit
    0.06
    ênh
    0.06
    atalog
    0.06
     litter
    0.06
    °
    0.06
     procure
    0.06
    Activations Density 0.000%

    No Known Activations