© 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. 19966
    Prev
    Next
    INDEX
    Explanations

    `@` symbol before column

    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
    uddy
    -0.05
    æѦè£ħ
    -0.05
    æķĻè®Ń
    -0.05
    iedo
    -0.05
    aised
    -0.05
    ä¸ĢæıIJ
    -0.05
    å©ļåIJİ
    -0.05
    æıIJ
    -0.05
    æ·ij
    -0.05
    ä¸ĢéŨ
    -0.05
    POSITIVE LOGITS
    ain
    0.06
    ilk
    0.06
    č↵↵
    0.05
    رÙĬ
    0.05
    atology
    0.05
    íķ´ëıĦ
    0.05
    tk
    0.05
    ÑĢÑĥм
    0.05
    ural
    0.05
    .k
    0.05
    Activations Density 0.041%

    No Known Activations