© 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. 17537
    Prev
    Next
    INDEX
    Explanations

    expresses love or liking

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    æĢ§æĪĸ
    -0.06
    auge
    -0.06
    зиÑĢованной
    -0.06
    aina
    -0.06
    μιÏĥ
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
     '{$
    -0.06
    ydd
    -0.06
    лови
    -0.05
    POSITIVE LOGITS
    ool
    0.07
    ä¸īéŨ
    0.06
    à¸ģารà¸ĵà¹Į
    0.06
    ÑĢо
    0.05
     ÑĢад
    0.05
     Ara
    0.05
    rawd
    0.05
     Ded
    0.05
    æľīè°ģ
    0.05
    wow
    0.05
    Activations Density 0.003%

    No Known Activations