© 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. 19126
    Prev
    Next
    INDEX
    Explanations

    piperidine derivatives

    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
    иков
    -0.06
    éĩijçłĸ
    -0.06
    æĭ¥
    -0.06
    ái
    -0.06
    ationen
    -0.06
     Shak
    -0.05
    ixo
    -0.05
    amkan
    -0.05
    åı£ä¸ŃçļĦ
    -0.05
    ivent
    -0.05
    POSITIVE LOGITS
    kit
    0.07
    ç¨Ģ
    0.06
    check
    0.06
    deles
    0.06
     checked
    0.05
    checked
    0.05
     dug
    0.05
    缸åħ³çļĦ
    0.05
     twitch
    0.05
    cook
    0.05
    Activations Density 0.004%

    No Known Activations