© 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. 53866
    Prev
    Next
    INDEX
    Explanations

    normal, standard, common

    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
    åħ¨åijĺ
    -0.11
    Ñģад
    -0.10
    acob
    -0.10
    ras
    -0.09
    çļĤ
    -0.09
    æ´»ä¸ĭåİ»
    -0.09
    .Factory
    -0.09
    åŀ£
    -0.09
    rats
    -0.09
     haystack
    -0.09
    POSITIVE LOGITS
    æĻ®éĢļçļĦ
    0.26
    常è§Ħ
    0.23
     обÑĭÑĩ
    0.22
    æĻ®éĢļ
    0.22
     ordinary
    0.20
    ä¼łç»ŁçļĦ
    0.17
    ordinary
    0.17
     normal
    0.16
    æŃ£å¸¸çļĦ
    0.16
     conventional
    0.16
    Activations Density 0.108%

    No Known Activations