© 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. 18944
    Prev
    Next
    INDEX
    Explanations

    semifinal games

    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
    olos
    -0.07
    Extern
    -0.07
    bourg
    -0.07
    incs
    -0.06
    eo
    -0.06
    inkt
    -0.06
    UnderTest
    -0.06
    ivil
    -0.06
    ục
    -0.06
    骨头
    -0.06
    POSITIVE LOGITS
     prochaine
    0.06
    rap
    0.05
    /
    0.05
    allen
    0.05
    æĺİæĺŁ
    0.05
    (
    0.05
    ä¸ĭä¸Ģ
    0.05
    åłµ
    0.05
    -
    0.05
    硬æĢ§
    0.05
    Activations Density 0.017%

    No Known Activations