© 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. 18961
    Prev
    Next
    INDEX
    Explanations

    compiled lists or guides

    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
    mals
    -0.05
     domen
    -0.05
    immen
    -0.05
    ä¸Ģ度
    -0.05
    irteen
    -0.05
     замÑĭ
    -0.05
     GPLv
    -0.05
    iches
    -0.05
            ↵    ↵
    -0.05
    å¾Ī好
    -0.05
    POSITIVE LOGITS
    çģ«
    0.06
    Ãłng
    0.06
    ickle
    0.06
    agne
    0.06
    -fire
    0.06
    ä¹ĭä¸ĭ
    0.05
    ç³»ç»ŁåĮĸ
    0.05
    ionato
    0.05
    ous
    0.05
    ä¸ĭäºĨ
    0.05
    Activations Density 0.012%

    No Known Activations