© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19163
    Prev
    Next
    INDEX
    Explanations

    religious institutions, temples, Gurdwaras, Sai Baba

    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
    bett
    -0.06
    çĦķ
    -0.06
    èĴ
    -0.06
    欢è¿İ
    -0.06
    å
    -0.06
     Purtroppo
    -0.06
    gleich
    -0.05
    Meeting
    -0.05
    ä¸ĩå²ģ
    -0.05
    ngoing
    -0.05
    POSITIVE LOGITS
    azy
    0.08
    ikel
    0.06
    zyst
    0.06
    çĥŃéŨæݨèįIJ
    0.06
    عÙĪ
    0.06
    ail
    0.06
    ffd
    0.05
    ierz
    0.05
    åĴĮ大
    0.05
    ÑģÑĤеÑĢ
    0.05
    Activations Density 0.010%

    No Known Activations