© 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. 27188
    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
    urre
    -0.08
    åįĪ
    -0.07
    订
    -0.07
    ç¥ĸ
    -0.07
    æŃ»
    -0.07
    à·ĥà·Ĭ
    -0.07
    æĪIJåĬŁä¸¾åĬŀ
    -0.06
    ỹ
    -0.06
    Filtered
    -0.06
    èģĶè°Ĭä¼ļ
    -0.06
    POSITIVE LOGITS
    otify
    0.07
    æī¬çļĦ
    0.07
    иÑĤоÑĢ
    0.07
    é¢ĿçļĦ
    0.07
    ouis
    0.07
     dituj
    0.07
    aging
    0.07
    çī¹å°Ķ
    0.07
    akuan
    0.07
    ierz
    0.06
    Activations Density 0.000%

    No Known Activations