© 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. 18219
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æī©å±ķèµĦæĸĻ
    -0.07
    lando
    -0.06
    åĴĮçĶ°
    -0.06
     ìĹ¬ê¸°ìĹIJ
    -0.06
    éĤĦ好
    -0.06
    空èĻļ
    -0.06
    znál
    -0.06
    irates
    -0.06
    ahl
    -0.06
    zers
    -0.06
    POSITIVE LOGITS
    icast
    0.06
    ardt
    0.05
    å½ĵåīį
    0.05
    æݨ
    0.05
    active
    0.05
    st
    0.05
    acht
    0.05
    浦
    0.05
    å®ŀ
    0.05
    çĤ¹åĪ°
    0.05
    Activations Density 0.000%

    No Known Activations