© 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. 20433
    Prev
    Next
    INDEX
    Explanations

    immediate actions or events

    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
    aner
    -0.06
    ely
    -0.06
    ippo
    -0.05
    uate
    -0.05
    PE
    -0.05
    å®ĩ
    -0.05
    تا
    -0.05
    T
    -0.05
    chst
    -0.05
     alternativa
    -0.05
    POSITIVE LOGITS
    eszcze
    0.06
    æ¸
    0.06
    urve
    0.06
    æİ¨è¿Ľä¼ļ
    0.06
    ниÑģÑĤи
    0.06
    edException
    0.06
    示èĮĥçĤ¹
    0.06
    åİĨæŶ
    0.06
    moth
    0.06
    æij¸æ¸ħ
    0.06
    Activations Density 0.004%

    No Known Activations