© 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. 20657
    Prev
    Next
    INDEX
    Explanations

    part of the game

    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
    MAND
    -0.06
    au
    -0.05
    ue
    -0.05
    εκ
    -0.05
    ubi
    -0.05
    oric
    -0.05
    HK
    -0.05
    éĻ©
    -0.05
    åİĨåı²æĢ§
    -0.05
    екÑģи
    -0.05
    POSITIVE LOGITS
    å¤ļ
    0.06
    edia
    0.06
    igan
    0.05
     efficiente
    0.05
    身
    0.05
    azing
    0.05
     instala
    0.05
    好
    0.05
    åIJĮ
    0.05
    erait
    0.05
    Activations Density 0.003%

    No Known Activations