© 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. 34437
    Prev
    Next
    INDEX
    Explanations

    you you your

    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
    æĩĤ
    -0.11
    åºĶæĶ¶
    -0.10
    象
    -0.10
    åĿĩä»·
    -0.09
    认å®ļ
    -0.09
    欢è¿İ大家
    -0.09
     наÑĢ
    -0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.09
    çħ§æł·
    -0.09
    æłĩéħį
    -0.09
    POSITIVE LOGITS
    éĻĽ
    0.09
    æıIJéĹ®
    0.09
    enne
    0.09
    MAS
    0.09
    ä¹ĥèĩ³
    0.09
    idal
    0.09
     Fasc
    0.08
    è¿Ļåı¥è¯Ŀ
    0.08
    å¨ij
    0.08
    Forg
    0.08
    Activations Density 0.040%

    No Known Activations