© 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. 27737
    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
    ï¸
    -0.08
    æĸĻ
    -0.07
    beh
    -0.06
    åĩºçº¿
    -0.06
    èĻij
    -0.06
     Cyr
    -0.06
    å²Ń
    -0.06
    éis
    -0.06
    ied
    -0.06
    ano
    -0.06
    POSITIVE LOGITS
    İĺ
    0.08
     (!!
    0.08
    nard
    0.08
    طرة
    0.08
    [Test
    0.08
    bench
    0.07
     "!
    0.07
     bench
    0.07
    ¤íĹ
    0.07
     Ñģложи
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.