© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37585
    Prev
    Next
    INDEX
    Explanations

    directions indicating location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åŀĵ
    -0.09
    é¡¿æŶ
    -0.08
     Underground
    -0.08
    éķ¿çŁŃ
    -0.08
    èĩªæĦ¿
    -0.08
    èĢĮå·²
    -0.08
    ä¸¥æł¼çļĦ
    -0.08
     Flying
    -0.08
    责任åĪ¶
    -0.08
    åı²ä¸ĬæľĢ
    -0.08
    POSITIVE LOGITS
    etimes
    0.10
    ally
    0.09
    most
    0.09
    ixon
    0.09
    NFL
    0.09
    èĢģçĪ¸
    0.08
    EMON
    0.08
    nty
    0.08
    æĻĥ
    0.08
    ockets
    0.08
    Activations Density 0.090%

    No Known Activations