© 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. 4515
    Prev
    Next
    INDEX
    Explanations

    how to achieve something

    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
    è¿ĺæľīä»Ģä¹Ī
    -0.09
    æķĻåŃ¦è´¨éĩı
    -0.09
    çļĦä¼łç»Ł
    -0.08
    æľīä»Ģä¹Ī
    -0.08
    欲
    -0.08
    å²ĺ
    -0.08
     Myst
    -0.08
    ç´į
    -0.08
    å¿ĥæĥ³
    -0.08
    贯彻èIJ½å®ŀ
    -0.07
    POSITIVE LOGITS
    æķĻä½ł
    0.12
    è®©ä½ł
    0.11
    atee
    0.10
    æĬĢå·§
    0.10
    误åĮº
    0.10
    ä¼ļè®©ä½ł
    0.09
    ä»»ä½ķ人éĥ½
    0.09
    Nib
    0.09
    CEL
    0.09
    æĻ®éĢļ人
    0.09
    Activations Density 0.124%

    No Known Activations