© 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. 20291
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    æīĢæľīçļĦ
    -0.06
     entire
    -0.06
    apé
    -0.06
    Fel
    -0.06
    idez
    -0.06
     Avi
    -0.05
    obl
    -0.05
    isses
    -0.05
    iking
    -0.05
    strom
    -0.05
    POSITIVE LOGITS
    inster
    0.06
    åıĪå¤ļ
    0.06
    yll
    0.05
     mapping
    0.05
    mapped
    0.05
     repl
    0.05
    èŃĺ
    0.05
    mapping
    0.05
    lee
    0.05
    æĺ¯å¤ļ
    0.05
    Activations Density 0.012%

    No Known Activations