© 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. 18705
    Prev
    Next
    INDEX
    Explanations

    life, survival, or price averages

    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
    åı¸
    -0.07
     presum
    -0.06
    SETTING
    -0.06
    onga
    -0.06
    产åĵģä¸Ńå¿ĥ
    -0.06
    OSO
    -0.06
    uccess
    -0.05
    yanto
    -0.05
    GENERAL
    -0.05
    su
    -0.05
    POSITIVE LOGITS
    æ¿
    0.05
    avier
    0.05
    帮
    0.05
    ائ
    0.05
    asty
    0.05
     br
    0.05
    ä¸ĵç§ij
    0.05
    .br
    0.05
    abe
    0.05
    ade
    0.05
    Activations Density 0.075%

    No Known Activations