© 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. 17067
    Prev
    Next
    INDEX
    Explanations

    ranked second after

    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
    ä¸ĢåĬł
    -0.07
    人æīĢ
    -0.07
    管æīĢ
    -0.07
    fér
    -0.06
    mara
    -0.06
    ÛĮشاÙĨ
    -0.06
    ÑĶм
    -0.06
    Äiju
    -0.06
    mal
    -0.06
    mis
    -0.06
    POSITIVE LOGITS
    лав
    0.06
    åĿĩ
    0.05
    太ç¥ĸ
    0.05
    enci
    0.05
    اء
    0.05
    lect
    0.05
    /
    0.05
    çĮ®
    0.05
     "
    0.05
    inen
    0.05
    Activations Density 0.106%

    No Known Activations