© 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. 22055
    Prev
    Next
    INDEX
    Explanations

    at the same time

    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
    mouth
    -0.06
    fica
    -0.05
    etc
    -0.05
    ish
    -0.05
    æĢ¥äºĨ
    -0.05
    зиÑĢов
    -0.05
    èİ«åıĬ
    -0.05
    Now
    -0.05
    Net
    -0.04
    éĢĶ
    -0.04
    POSITIVE LOGITS
    ijo
    0.06
    äºĨ对
    0.06
    éĢļ讯社
    0.06
    untut
    0.06
    enta
    0.06
    å®ĥåħ·æľī
    0.06
    appare
    0.06
    çļĦ年轻人
    0.06
    å·¥ä½ľèĥ½åĬĽ
    0.06
    essim
    0.06
    Activations Density 0.015%

    No Known Activations