© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21493
    Prev
    Next
    INDEX
    Explanations

    cl

    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
    عÙħ
    -0.06
    天平
    -0.06
    ç§
    -0.06
    ses
    -0.06
    -0.06
     gesta
    -0.06
     wujud
    -0.06
    å¯¹æľªæĿ¥
    -0.06
    åĪĢåŃIJ
    -0.06
    ount
    -0.06
    POSITIVE LOGITS
    cl
    0.05
     ala
    0.05
    ivia
    0.05
    带çļĦ
    0.05
     cons
    0.05
    anka
    0.05
    alloca
    0.05
    icy
    0.05
    带ä¸Ĭ
    0.05
     cl
    0.05
    Activations Density 0.464%

    No Known Activations