© 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. 21922
    Prev
    Next
    INDEX
    Explanations

    symptomatic effusion

    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
    elde
    -0.07
    adurch
    -0.06
    æķ´åº§
    -0.06
    ute
    -0.06
    åĽŀåİ»åIJ§
    -0.06
     estiv
    -0.06
    ouver
    -0.06
    å¤ĸåŀĭ
    -0.06
    ermen
    -0.06
     erm
    -0.06
    POSITIVE LOGITS
     unt
    0.05
    éĢļ
    0.05
    aj
    0.05
    æĪª
    0.05
     rom
    0.05
     uns
    0.05
    èĢ
    0.05
    ç´§è¦ģ
    0.05
    ظ
    0.05
     absolut
    0.05
    Activations Density 0.007%

    No Known Activations