© 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. 13960
    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
    uest
    -0.08
    å¯¹çĽ¸åħ³
    -0.07
    igkeit
    -0.07
    нок
    -0.06
    å¤Ħ女
    -0.06
    icar
    -0.06
    vel
    -0.06
    ugel
    -0.06
    åįķ
    -0.06
     наклад
    -0.06
    POSITIVE LOGITS
    ulled
    0.08
    iley
    0.08
    éļ¨
    0.07
    abet
    0.07
    é¡¹çĽ®å®ŀæĸ½
    0.07
    baz
    0.07
    éļı
    0.07
    éļıçĿĢ社ä¼ļ
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    çīĩçļĦ
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.