© 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. 19627
    Prev
    Next
    INDEX
    Explanations

    comma followed by "which" or "The"

    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
    æĪĸå¤ļ
    -0.06
    inals
    -0.06
    olland
    -0.06
    inach
    -0.06
    -print
    -0.06
    menge
    -0.06
    erts
    -0.06
    assed
    -0.06
    aldo
    -0.06
    geries
    -0.06
    POSITIVE LOGITS
    ol
    0.06
    uffy
    0.05
    idae
    0.05
    åħ®
    0.05
    uff
    0.05
    l
    0.05
    ull
    0.05
    è¦ļ
    0.05
    åĶ¬
    0.05
    æ·±
    0.05
    Activations Density 0.113%

    No Known Activations