© 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. 19987
    Prev
    Next
    INDEX
    Explanations

    ability to achieve or maintain

    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
    yet
    -0.06
    eldo
    -0.06
    åĴı
    -0.06
    åł¡
    -0.05
    견
    -0.05
    หั
    -0.05
    èĭ
    -0.05
    Ùĩد
    -0.05
    генÑĤ
    -0.05
     ÙģرÙĪ
    -0.05
    POSITIVE LOGITS
    adre
    0.05
    åħ¼
    0.05
     thereof
    0.05
     serp
    0.05
    åĬ¡
    0.05
    éĢĤ
    0.05
    ardan
    0.05
    Need
    0.05
    çļĦæľīæķĪæĢ§
    0.05
    interrupt
    0.05
    Activations Density 0.035%

    No Known Activations