© 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. 19070
    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
    ä¸įæĶ¾
    -0.07
    odash
    -0.07
    _locals
    -0.07
    è·¯æĺĵ
    -0.07
    quoise
    -0.07
    jenigen
    -0.06
    çĤ¹æ»´
    -0.06
    å±ŀ
    -0.06
     donate
    -0.06
    arton
    -0.06
    POSITIVE LOGITS
    ľ
    0.07
    isson
    0.07
    aju
    0.07
     wrong
    0.07
    itch
    0.07
    æ¿ĢåıijåѦçĶŁ
    0.07
    ç«Ļå¼ı
    0.06
    å¤ļåĽĬ
    0.06
    è¾ĥæĹ©
    0.06
    aja
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.