© 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. 3624
    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
    istrator
    -0.11
    ĥ½
    -0.10
    isses
    -0.09
    uard
    -0.09
    ipment
    -0.09
    еÑĢÑĮ
    -0.09
    é¹ıé£ŀ
    -0.09
    ÃīR
    -0.09
    erais
    -0.09
     não
    -0.09
    POSITIVE LOGITS
    ional
    0.11
     necessarily
    0.09
    HING
    0.09
    zsche
    0.08
    ching
    0.08
    éĤ£ä¹Ī容æĺĵ
    0.08
    ive
    0.08
    ch
    0.08
     obstante
    0.08
    withstanding
    0.08
    Activations Density 0.000%

    No Known Activations