© 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. 19980
    Prev
    Next
    INDEX
    Explanations

    health outcomes and behaviors

    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
    atoare
    -0.07
    طة
    -0.06
    kut
    -0.06
     bantu
    -0.06
    eut
    -0.06
    acc
    -0.05
    Error
    -0.05
    engaruh
    -0.05
    awk
    -0.05
    ØŃتÙĩا
    -0.05
    POSITIVE LOGITS
    åıĹ
    0.07
    æĥľ
    0.06
    affected
    0.06
    ügy
    0.05
    èĥ
    0.05
    éĿ¢åĢĴ
    0.05
     cái
    0.05
    å´©
    0.05
    bery
    0.05
    é£
    0.05
    Activations Density 0.136%

    No Known Activations