© 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. 4410
    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
    æŃ£åıį
    -0.08
    atia
    -0.08
    <|box_end|>
    -0.08
    FormatException
    -0.07
    åıĬè¦ģæ±Ĥ
    -0.07
    quilib
    -0.07
    à¤ķà¥ģ
    -0.07
    ä¼ĺåħĪèĢĥèĻij
    -0.07
    西å¸Ĥ
    -0.07
    _UNICODE
    -0.07
    POSITIVE LOGITS
    adar
    0.08
    /
    0.07
    hie
    0.07
    _*
    0.07
    aily
    0.06
    untas
    0.06
    åĩĢ
    0.06
    /reference
    0.06
    ional
    0.06
     metric
    0.06
    Activations Density 0.051%

    No Known Activations