© 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. 17025
    Prev
    Next
    INDEX
    Explanations

    vital coupled with core concepts

    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
    ocado
    -0.07
    orte
    -0.07
    ì°į
    -0.06
    менов
    -0.06
    virt
    -0.06
    æĮĻ
    -0.06
    æĬķèµĦä»·åĢ¼
    -0.06
    åħ¬å¹³åħ¬æŃ£
    -0.06
    ovu
    -0.06
    ikul
    -0.06
    POSITIVE LOGITS
    æŶåĢĻ
    0.07
    ÙĬØŃ
    0.07
    ÙĬ
    0.06
    pered
    0.06
    SystemService
    0.05
    ä¸įæģ¯
    0.05
    /ext
    0.05
    ible
    0.05
    åIJ¦
    0.05
    i
    0.05
    Activations Density 0.005%

    No Known Activations