© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36173
    Prev
    Next
    INDEX
    Explanations

    thus followed by a result

    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
    äºİæĺ¯
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    æĸ¼æĺ¯
    -0.09
    éĤ£ä¹Ī
    -0.09
    è¿Ļæīį
    -0.08
    rest
    -0.08
    éħ¸
    -0.08
    athan
    -0.08
    æŀľçĦ¶
    -0.08
     cui
    -0.08
    POSITIVE LOGITS
    ly
    0.13
    forth
    0.12
    å¡ŀ
    0.10
    ãģ¨ãģĦãģ£ãģ¦
    0.09
    çĦ¶æĺ¯
    0.09
    енно
    0.09
    ual
    0.09
    à¸ģระà¸Ĺ
    0.08
    ally
    0.08
    onus
    0.08
    Activations Density 0.029%

    No Known Activations