© 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. 21889
    Prev
    Next
    INDEX
    Explanations

    in water or oil

    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
    iya
    -0.07
    以å¾Ģ
    -0.07
     interiores
    -0.06
    imiz
    -0.06
    ÏĢι
    -0.06
    uvi
    -0.06
    onnen
    -0.06
    umen
    -0.06
    æĮ¥éľį
    -0.06
    রা
    -0.06
    POSITIVE LOGITS
    å±Ī
    0.06
    æݥ触çļĦ
    0.05
    odia
    0.05
    agnes
    0.05
     cruc
    0.05
    ood
    0.05
    ahan
    0.05
    ütz
    0.05
    bon
    0.05
    frey
    0.05
    Activations Density 0.034%

    No Known Activations