© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21159
    Prev
    Next
    INDEX
    Explanations

    following questions on how to perform actions

    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
    éģį
    -0.05
    à¸Ĭà¸Ļ
    -0.05
    ago
    -0.05
     поÑħод
    -0.05
    ona
    -0.05
     ate
    -0.05
    ä¸į许
    -0.05
    pier
    -0.05
    æ¶ĪåĮĸçļĦ
    -0.05
     engulf
    -0.05
    POSITIVE LOGITS
    æĬĺ弯
    0.06
    ä¸Ń磩
    0.06
    ä¿¡ä¸Ń
    0.06
    ombo
    0.05
     Yüks
    0.05
    rique
    0.05
    idin
    0.05
     osta
    0.05
     specific
    0.05
    çłĶç©¶å·¥ä½ľ
    0.05
    Activations Density 0.023%

    No Known Activations