© 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. 18053
    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
    Ñı
    -0.06
     “
    -0.05
    tg
    -0.05
    azah
    -0.05
     clutch
    -0.05
     nich
    -0.05
    ties
    -0.05
    å°ıä¼Ĺ
    -0.05
    ftime
    -0.05
    è¾Ī
    -0.05
    POSITIVE LOGITS
    cock
    0.06
    屡次
    0.05
    åĪ®
    0.05
    æĹłæķ°æ¬¡
    0.05
    çļĦæľĢé«ĺ
    0.05
    çŃīä¸Ģç³»åĪĹ
    0.05
    ä¸ĸçķĮä¸ĬæľĢ
    0.05
     Secretario
    0.05
    åħ¶ä¸ŃæľĢ
    0.05
    æī°
    0.05
    Activations Density 0.000%

    No Known Activations