© 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. 56861
    Prev
    Next
    INDEX
    Explanations

    Chrysler, launches, cholesteric

    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
    åī©ä¸ĭ
    -0.09
    è¦ģç´§
    -0.09
    auer
    -0.09
    лиÑĤ
    -0.08
    çĬ¯ç½ªå«Įçĸij
    -0.08
    æ»ĭ润
    -0.08
    /non
    -0.08
    ãģĦãģĨ
    -0.08
    顺åĪ©å®ĮæĪIJ
    -0.08
    ixe
    -0.08
    POSITIVE LOGITS
    ively
    0.09
    resenter
    0.09
    çIJ´
    0.09
    åIJī
    0.09
    äºĨä¸Ģ份
    0.09
    ÑıÑī
    0.09
    orbit
    0.08
    ienne
    0.08
    ãģ¹ãģį
    0.08
    centaje
    0.08
    Activations Density 0.002%

    No Known Activations