© 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. 19256
    Prev
    Next
    INDEX
    Explanations

    finite state machine transitions

    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
    ÑĪенÑĮ
    -0.07
    rÃł
    -0.07
    大åĪ©
    -0.07
     Apar
    -0.07
    enzio
    -0.07
    agne
    -0.06
    ç½ij绾æĬĢæľ¯
    -0.06
    gab
    -0.06
    loads
    -0.06
    ׼×ķ׾
    -0.06
    POSITIVE LOGITS
    梨èĬ±
    0.06
    otp
    0.06
    -
    0.05
    éħ°
    0.05
    bomb
    0.05
    缸
    0.05
    berg
    0.05
    丢
    0.05
     transition
    0.05
    çļĦ说
    0.05
    Activations Density 0.010%

    No Known Activations