© 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. 18578
    Prev
    Next
    INDEX
    Explanations

    have been

    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
    è´¨çļĦ
    -0.07
    éĩ
    -0.07
    обÑĢ
    -0.06
    بØŃ
    -0.06
    nya
    -0.06
    elage
    -0.06
    ablish
    -0.06
    ged
    -0.06
    cience
    -0.06
    æ·¼
    -0.06
    POSITIVE LOGITS
    er
    0.08
    able
    0.07
    Ñı
    0.06
    um
    0.06
    ment
    0.06
    aler
    0.06
    stration
    0.06
    ishing
    0.05
    oval
    0.05
    eer
    0.05
    Activations Density 0.102%

    No Known Activations