© 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. 19475
    Prev
    Next
    INDEX
    Explanations

    physics vector components

    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
    ä¸Ĭå½ĵ
    -0.06
    agram
    -0.06
    åĽ¾çīĩ
    -0.05
    lime
    -0.05
    æĬij
    -0.05
    ç®Ģä½ĵ
    -0.05
     upp
    -0.05
    sembly
    -0.05
    æ¼Ķ
    -0.05
    leon
    -0.05
    POSITIVE LOGITS
    æĺŁæµ·
    0.06
    jÃł
    0.06
    稳å®ļåĴĮ
    0.06
    æįº
    0.05
    ª
    0.05
    ánchez
    0.05
    åı£éķĩ
    0.05
    entra
    0.05
    =""></
    0.05
     finally
    0.05
    Activations Density 0.004%

    No Known Activations