© 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. 20480
    Prev
    Next
    INDEX
    Explanations

    see a

    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
    รà¹īาย
    -0.06
    ì°©
    -0.05
    éĽ¾
    -0.05
    æīĢå¾Ĺ
    -0.05
     implicitly
    -0.05
     Word
    -0.05
    ×ķת
    -0.05
     주목
    -0.05
    ä¸İå®ŀè·µ
    -0.05
    аеÑĤ
    -0.05
    POSITIVE LOGITS
    æīįè¡Į
    0.07
    ackle
    0.06
    笳
    0.06
    æīį对
    0.06
    hrad
    0.06
    ä¸įçĦ¶
    0.06
    å·´åħĭ
    0.06
    æĿ¥åIJ§
    0.06
    наÑĩе
    0.06
    exas
    0.06
    Activations Density 0.032%

    No Known Activations