© 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. 18569
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    urun
    -0.07
    驼
    -0.06
    uctions
    -0.06
    ä¾
    -0.06
    ORIZ
    -0.06
    æł¡
    -0.05
     ÙĨعÙħ
    -0.05
    麻çĥ¦
    -0.05
    æ¯Ķå¦Ĥ
    -0.05
    ãĤī
    -0.05
    POSITIVE LOGITS
    ament
    0.07
    ien
    0.06
    anto
    0.06
    wad
    0.05
    åīįäºĶ
    0.05
    ÑĮми
    0.05
     import
    0.05
    ÑĤÑİ
    0.05
    em
    0.05
    iej
    0.05
    Activations Density 0.100%

    No Known Activations