© 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. 27457
    Prev
    Next
    INDEX
    Explanations

    twists and entanglement

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    驻马
    -0.08
    æ´¾åĩº
    -0.07
     hail
    -0.07
    ãĥ©ãĥ«
    -0.07
    _PUR
    -0.07
     decentral
    -0.07
     sip
    -0.07
    èİ«åıĬ
    -0.07
    ENDA
    -0.06
     suss
    -0.06
    POSITIVE LOGITS
    ç¼łç»ķ
    0.10
    strand
    0.08
     crossings
    0.08
     wrapping
    0.08
    漩涡
    0.08
    æĭĵæīij
    0.08
     strands
    0.07
     twists
    0.07
    ç´
    0.07
    解å¼Ģ
    0.07
    Activations Density 0.005%

    No Known Activations