© 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. 17838
    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
    ohn
    -0.06
    çľĭä¼¼
    -0.06
    æıIJ
    -0.06
    åĩłåĪĨ
    -0.05
    大èĩ´
    -0.05
    è¿°
    -0.05
    illos
    -0.05
     Ñģал
    -0.05
     ret
    -0.05
    æľīçĤ¹åĦ¿
    -0.05
    POSITIVE LOGITS
    *”.
    0.07
     optimal
    0.06
    èĶĶ
    0.06
     âĤ¬.
    0.06
    âĤ¬.
    0.06
    ayat
    0.06
    UNUSED
    0.06
    ”*.
    0.06
    !».
    0.06
     Consulta
    0.06
    Activations Density 0.000%

    No Known Activations