© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 24426
    Prev
    Next
    INDEX
    Explanations

    Russian conjunctions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪ©
    -0.07
    åµĺ
    -0.07
    大åı¯
    -0.07
    ä¸Ģå¤ķ
    -0.07
    太éļ¾
    -0.07
    ÏģÏīν
    -0.07
    å°¼
    -0.07
    ervas
    -0.06
    heit
    -0.06
    åIJį
    -0.06
    POSITIVE LOGITS
    anan
    0.07
    okka
    0.07
    acco
    0.07
    .Shared
    0.07
    arem
    0.07
    .Guid
    0.07
    гоÑĢод
    0.06
    anser
    0.06
    rome
    0.06
    ãĤ·ãĥ§
    0.06
    Activations Density 0.574%

    No Known Activations