© 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. 21841
    Prev
    Next
    INDEX
    Explanations

    work experience and career details

    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
    {/
    -0.06
    GenerationStrategy
    -0.06
    _HIDDEN
    -0.06
    ÄįiÄĩ
    -0.06
    .Generation
    -0.06
    ÙĥØ©
    -0.06
    å¤ļæݪ并举
    -0.06
     combusti
    -0.06
    彿
    -0.06
    æı
    -0.06
    POSITIVE LOGITS
    /sites
    0.05
    åīįå¾Ģ
    0.05
    zia
    0.05
    ep
    0.05
    apun
    0.05
    ä»Ĭ天æĻļä¸Ĭ
    0.05
     -
    0.04
    æľīæķĪæݧåĪ¶
    0.04
    ä¸Ģ个个
    0.04
    assen
    0.04
    Activations Density 0.005%

    No Known Activations