© 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. 20642
    Prev
    Next
    INDEX
    Explanations

    Russian phrases indicating inability/difficulty

    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
    ence
    -0.07
    sweise
    -0.07
    en
    -0.07
    RODUCTION
    -0.06
    ι
    -0.06
    tanda
    -0.06
    ÙıÙħÙĴ
    -0.06
    ing
    -0.06
    ulum
    -0.06
     лик
    -0.06
    POSITIVE LOGITS
    ively
    0.06
    ãĥ¼ãĤ¸ãĥ£
    0.06
    ़
    0.06
    æĺ¾èĢĮæĺĵè§ģ
    0.05
    immun
    0.05
    .localtime
    0.05
    clair
    0.05
    eur
    0.05
    gleich
    0.05
    isted
    0.05
    Activations Density 0.001%

    No Known Activations