© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22007
    Prev
    Next
    INDEX
    Explanations

    regular expression capture groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩĺ
    -0.07
     kÃŃs
    -0.06
    esk
    -0.06
    é©ħ
    -0.06
     discre
    -0.06
    rÃŃ
    -0.06
    転
    -0.06
     laga
    -0.06
    erver
    -0.06
    ullo
    -0.06
    POSITIVE LOGITS
    abe
    0.05
    egend
    0.05
    inct
    0.05
     titular
    0.05
     wre
    0.05
    .offsetWidth
    0.05
    okes
    0.04
    姥
    0.04
    aupt
    0.04
    çݯç»ķ
    0.04
    Activations Density 0.006%

    No Known Activations