© 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. 18399
    Prev
    Next
    INDEX
    Explanations

    lists with conjunctions

    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
    æľŁåĪĿ
    -0.06
    ä»¥ä¹łè¿ijå¹³
    -0.05
    ÙħÙĪ
    -0.05
    å¾ĹéĿŀ常
    -0.05
    доÑħ
    -0.05
    amn
    -0.05
    omat
    -0.05
    åĢĻéĢī
    -0.05
    gement
    -0.05
    æīĢè¦ģ
    -0.05
    POSITIVE LOGITS
    /or
    0.06
    讲究
    0.05
    åĴĮ
    0.05
    ÙĨائÙĬØ©
    0.05
    è¾Ł
    0.05
    пли
    0.05
    reten
    0.05
    ثرة
    0.05
     rame
    0.05
    beitrag
    0.05
    Activations Density 0.015%

    No Known Activations