© 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. 18531
    Prev
    Next
    INDEX
    Explanations

    medical diagnosis, diagnosed, established

    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
    setValue
    -0.07
    约å®ļçļĦ
    -0.06
    ä¸¥æł¼æĮīçħ§
    -0.06
    è§ĦèĮĥ
    -0.06
    atile
    -0.06
    kový
    -0.06
    ä¸īä¸Ń
    -0.06
    ombo
    -0.06
     obiett
    -0.06
     Ive
    -0.06
    POSITIVE LOGITS
    ese
    0.06
    ise
    0.05
    olem
    0.05
    ugg
    0.05
    chl
    0.05
    èį£
    0.05
    åĽłæŀľ
    0.05
    çľĭå¾ħ
    0.05
    æĪIJç«ĭ
    0.05
     subj
    0.05
    Activations Density 0.010%

    No Known Activations