© 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. 17376
    Prev
    Next
    INDEX
    Explanations

    known as

    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
    رة
    -0.06
    ذج
    -0.06
    awah
    -0.06
     ideally
    -0.06
    aire
    -0.06
    inery
    -0.06
    strup
    -0.06
     Liber
    -0.06
    åįij
    -0.06
    ews
    -0.05
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.06
    åħ¶èº«
    0.05
    身边çļĦ
    0.05
    ä¹ĭä¸Ģ
    0.05
    ped
    0.05
    çļĦåĪ°æĿ¥
    0.05
    aut
    0.05
    osa
    0.05
     liter
    0.05
    æIJŀ
    0.05
    Activations Density 0.029%

    No Known Activations