© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35284
    Prev
    Next
    INDEX
    Explanations

    consumer behavior

    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
    æĪIJæŀľè½¬åĮĸ
    -0.09
    åĬŁè¯¾
    -0.09
    ä»İä¸ļ
    -0.09
    ned
    -0.09
    eding
    -0.09
    ness
    -0.08
    locks
    -0.08
    /we
    -0.08
    ç²¥
    -0.08
    èĢģ人家
    -0.08
    POSITIVE LOGITS
    hip
    0.11
    ä¹ŁæŃ£æĺ¯
    0.10
    -facing
    0.10
    åĿŀ
    0.10
    æľĭåıĭ们
    0.10
    -friendly
    0.09
    iser
    0.09
    ized
    0.09
    åįıä¼ļ
    0.09
    hk
    0.09
    Activations Density 0.016%

    No Known Activations