© 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. 18324
    Prev
    Next
    INDEX
    Explanations

    police work

    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
    iesta
    -0.05
     secured
    -0.05
    ↵      ↵
    -0.05
     Cock
    -0.05
    olso
    -0.05
    éģºæĨ¾
    -0.05
     Bug
    -0.05
    ored
    -0.05
    eren
    -0.05
    èħ®
    -0.05
    POSITIVE LOGITS
    rum
    0.08
     admit
    0.06
    clinic
    0.06
     veille
    0.06
    就好
    0.06
    idd
    0.05
    æĻ®éĢļ
    0.05
    ugo
    0.05
    å¤ļ空
    0.05
    ä¸įå®ī
    0.05
    Activations Density 0.001%

    No Known Activations