© 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. 18403
    Prev
    Next
    INDEX
    Explanations

    be

    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
    缮çĿ¹
    -0.06
    å°ģåı£
    -0.06
     Implements
    -0.06
    hÃłnh
    -0.05
     Reinigungs
    -0.05
    venida
    -0.05
     netto
    -0.05
    è´Ń
    -0.05
    å®ŀæĸ½æĸ¹å¼ı
    -0.05
    à¥Įर
    -0.05
    POSITIVE LOGITS
    oulder
    0.06
     positivity
    0.05
    çĤ¹ä½į
    0.05
     turnaround
    0.05
    åij¨è½¬
    0.05
    ÑĬ
    0.05
     quý
    0.05
    azel
    0.05
    alli
    0.05
    æķĸ
    0.05
    Activations Density 0.018%

    No Known Activations