© 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. 11192
    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
    对产åĵģ
    -0.07
    KE
    -0.06
    èĦ¸èĽĭ
    -0.06
    zuk
    -0.06
    ooks
    -0.06
     repre
    -0.06
    ç»Ħç»ĩä¸Ń
    -0.06
    aket
    -0.06
    åĶ¾
    -0.06
    çļĦæĺ¯ä»Ģä¹Ī
    -0.06
    POSITIVE LOGITS
    oration
    0.07
     asisti
    0.07
    èĢģçĪ·
    0.07
     Quer
    0.07
    iero
    0.07
    åĶIJ家
    0.07
    atil
    0.07
     Aless
    0.07
    пени
    0.07
    IBC
    0.06
    Activations Density 0.000%

    No Known Activations