© 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. 20707
    Prev
    Next
    INDEX
    Explanations

    arrays of integers

    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
     Bottom
    -0.05
     bottom
    -0.05
    åIJĮä»ģ
    -0.05
    uilt
    -0.05
    ê°IJ
    -0.05
    imbang
    -0.05
    éĿĵ
    -0.05
    æĺ±
    -0.05
    оÑģÑĥ
    -0.05
    iggs
    -0.05
    POSITIVE LOGITS
    çĻ¾äºº
    0.07
    vens
    0.06
    ä¸įåıĹ
    0.05
     ÑģамиÑħ
    0.05
     individual
    0.05
    们çļĦ
    0.05
    à¸ģัà¸Ļà¹Ħà¸Ķà¹ī
    0.05
    serde
    0.05
     reliably
    0.05
     Ø£ÙģرÙĬÙĤÙĬا
    0.05
    Activations Density 0.010%

    No Known Activations