© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19096
    Prev
    Next
    INDEX
    Explanations

    in phrases

    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
    åIJĦèĩªçļĦ
    -0.06
    odus
    -0.06
    odom
    -0.06
    æīįçŁ¥éģĵ
    -0.05
    æį®æĤī
    -0.05
    ãģĿãĤĮãģŀãĤĮãģ®
    -0.05
    è®°èĢħäºĨ解åĪ°
    -0.05
    unta
    -0.05
    æīįå¾Ĺ以
    -0.05
    aÄĩ
    -0.05
    POSITIVE LOGITS
    å¾Ģ
    0.06
     experimenting
    0.06
    crete
    0.06
    æ³Ľ
    0.06
    anker
    0.05
    warts
    0.05
    æľīæľº
    0.05
    anked
    0.05
    uts
    0.05
    æĪijæĥ³
    0.05
    Activations Density 0.014%

    No Known Activations