© 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. 20030
    Prev
    Next
    INDEX
    Explanations

    niche topic interest vertical

    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
     capture
    -0.06
    izz
    -0.06
    纳西
    -0.05
    ÙĬات
    -0.05
    à¸ķรา
    -0.05
    ectividad
    -0.05
    penas
    -0.05
    hin
    -0.05
    ynthesis
    -0.05
    ä½ľä¸ºä¸Ģ项
    -0.05
    POSITIVE LOGITS
    ì§IJ
    0.06
    人群ä¸Ń
    0.06
    remium
    0.06
    为æłĩåĩĨ
    0.05
    åľŁåľ°ä¸Ĭ
    0.05
    çļĦä¸ĵä¸ļ
    0.05
    å°Īæ¥Ń
    0.05
    ubil
    0.05
    è°Ĭ
    0.05
    enko
    0.05
    Activations Density 0.002%

    No Known Activations