© 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. 20115
    Prev
    Next
    INDEX
    Explanations

    encounter

    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
    ally
    -0.07
    art
    -0.06
    pies
    -0.06
     lay
    -0.06
    etti
    -0.06
    ÙĪع
    -0.06
    оÑģÑĤи
    -0.06
    kait
    -0.06
    Ø·
    -0.06
    POSITIVE LOGITS
    IgnoreCase
    0.07
    antie
    0.07
    iper
    0.06
    edException
    0.06
    able
    0.06
    ÑģÑı
    0.06
    ì§ij
    0.06
    rovers
    0.06
    ablemente
    0.06
    sworth
    0.06
    Activations Density 0.005%

    No Known Activations