© 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. 19974
    Prev
    Next
    INDEX
    Explanations

    village of

    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
    们
    -0.06
    amedi
    -0.06
    elsea
    -0.05
    in
    -0.05
    ç«£
    -0.05
    news
    -0.05
    æĸĩæijĺ
    -0.05
    spe
    -0.05
    atamente
    -0.05
    ifle
    -0.05
    POSITIVE LOGITS
    ulate
    0.08
     illet
    0.07
    rist
    0.07
    quê
    0.06
    hood
    0.06
    óta
    0.06
    intervista
    0.06
    ains
    0.06
    ulates
    0.06
    tare
    0.06
    Activations Density 0.008%

    No Known Activations