© 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. 19965
    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
     Ded
    -0.08
    è¾ĥæĹ©
    -0.08
    usak
    -0.07
    èĬ±æĹĹ
    -0.07
    éģĩä¸Ĭ
    -0.07
    çĥĤ
    -0.07
    ccio
    -0.07
    coce
    -0.07
    ability
    -0.07
    ittest
    -0.07
    POSITIVE LOGITS
     downstream
    0.07
    æģ¼
    0.07
    ä¸ĭ游
    0.07
    lov
    0.06
    ilden
    0.06
    gross
    0.06
    mir
    0.06
     nic
    0.06
     gross
    0.06
    ä»ĵ
    0.06
    Activations Density 0.000%

    No Known Activations