© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19731
    Prev
    Next
    INDEX
    Explanations

    information followed by acquisition or applicability

    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
    ждÑĥÑİ
    -0.07
    çļĦä»»åĬ¡
    -0.07
    пÑĥÑĤ
    -0.07
     Ñĥп
    -0.06
    arina
    -0.06
    ÙĪاء
    -0.06
    ä¸į注æĦı
    -0.06
    ities
    -0.06
    جÙĪÙĨ
    -0.06
    ваÑħ
    -0.06
    POSITIVE LOGITS
     foregoing
    0.06
    åħ¶äºĮ
    0.06
     Äiju
    0.05
    ichi
    0.05
     latter
    0.05
    åĪ©
    0.05
     compiled
    0.05
    ä½łæľĢ
    0.05
    èĮľ
    0.05
     replicated
    0.05
    Activations Density 0.013%

    No Known Activations