© 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. 22267
    Prev
    Next
    INDEX
    Explanations

    miracles and healing

    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
    esame
    -0.06
    umble
    -0.06
    idea
    -0.06
    goed
    -0.06
    egang
    -0.06
    رÙĬبة
    -0.06
    cken
    -0.06
    สมา
    -0.06
    çīĪ车åŀĭ
    -0.06
    mine
    -0.06
    POSITIVE LOGITS
    ities
    0.06
    èĥĮåIJİçļĦ
    0.06
    çļĦèĥĮåIJİ
    0.06
    èĥĮåIJİ
    0.05
     miracle
    0.05
    aisen
    0.05
    æŶæľīåıijçĶŁ
    0.05
    çİ°åľº
    0.05
    åĽŀå¤į
    0.05
    äºĭåĦ¿
    0.05
    Activations Density 0.011%

    No Known Activations