© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19742
    Prev
    Next
    INDEX
    Explanations

    NVIDIA corporation

    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
    s
    -0.06
    inde
    -0.06
    ors
    -0.06
    ening
    -0.06
    er
    -0.06
    è¾¹çļĦ
    -0.05
    个
    -0.05
    çķĻæĦı
    -0.05
    ence
    -0.05
    ÑģнÑĥ
    -0.05
    POSITIVE LOGITS
    koch
    0.06
    STA
    0.06
    tschaft
    0.06
    assis
    0.06
     tremend
    0.06
    orte
    0.06
    èĻĶ
    0.06
    çĽħ
    0.06
    otis
    0.06
    tua
    0.06
    Activations Density 0.001%

    No Known Activations