© 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. 19947
    Prev
    Next
    INDEX
    Explanations

    each contains

    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
    è§ĦèĮĥ
    -0.05
    uar
    -0.05
    eng
    -0.05
    å¾Ĺåĥı
    -0.05
    èī²å½©
    -0.05
    oren
    -0.05
    åĥı个
    -0.05
    赤åŃĹ
    -0.05
     Hol
    -0.05
    æĺİæĺ¾
    -0.05
    POSITIVE LOGITS
     EVER
    0.07
     EACH
    0.06
    IFY
    0.06
    weig
    0.06
     Ever
    0.06
    æı
    0.06
     Reyn
    0.06
    каÑģ
    0.06
    人ä¼ļ
    0.06
    unner
    0.06
    Activations Density 0.002%

    No Known Activations