© 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. 19873
    Prev
    Next
    INDEX
    Explanations

    improve, increase, maximize, enhance

    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
    ãĥªãĥ¼ãĥī
    -0.06
    дев
    -0.06
    utzer
    -0.06
    iega
    -0.06
    误
    -0.06
    edos
    -0.06
    дений
    -0.06
    誤
    -0.06
    éĩįéĩį
    -0.05
    æĹłä»İ
    -0.05
    POSITIVE LOGITS
    æĬ
    0.05
     nochmals
    0.05
     bothered
    0.05
     determinados
    0.05
    è¿Ļ个åĽŀçŃĶ
    0.05
     determinadas
    0.05
    åĨ³å®ļçļĦ
    0.05
    继æī¿äºĨ
    0.05
    iry
    0.05
     lifetime
    0.05
    Activations Density 0.031%

    No Known Activations