© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36965
    Prev
    Next
    INDEX
    Explanations

    make it work

    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
    æĹłæķĮ
    -0.09
    æģį
    -0.09
    å¤©åľ°
    -0.09
    æ´Ļ
    -0.08
    dia
    -0.08
    æĺ¯åIJ¦æľī
    -0.08
     оÑĤдел
    -0.08
    éĿ¢ä¸´çļĦ
    -0.08
    OMIC
    -0.08
    verts
    -0.08
    POSITIVE LOGITS
    è¿IJä½ľ
    0.15
     funciona
    0.15
    working
    0.14
     working
    0.13
     works
    0.13
    -working
    0.13
     functioning
    0.13
    åıijæĮ¥ä½ľçĶ¨
    0.13
     workings
    0.13
     ÑĢабоÑĤаеÑĤ
    0.12
    Activations Density 0.370%

    No Known Activations