© 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. 46296
    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
    untut
    -0.07
    åŃ¦æł¡é¢Ĩ导
    -0.07
    ampo
    -0.07
    à¸ļัà¸Ķ
    -0.07
    amac
    -0.07
    亥
    -0.07
    ccione
    -0.07
    piel
    -0.07
    大æľīåı¯ä¸º
    -0.07
    ê°ģ
    -0.07
    POSITIVE LOGITS
    ippi
    0.07
    हि
    0.07
     sole
    0.07
    miet
    0.07
    ä¹IJ
    0.06
    串
    0.06
    izioni
    0.06
    å¤Ħ
    0.06
    åıĪä¸į
    0.06
    år
    0.06
    Activations Density 0.000%

    No Known Activations