© 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. 27056
    Prev
    Next
    INDEX
    Explanations

    age-related decline

    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
    å¨ĵ
    -0.10
    çĺ¾
    -0.10
    æķij人
    -0.09
    æĪŁ
    -0.09
    伪è£ħ
    -0.09
     segment
    -0.09
    çĸ¯çĭĤ
    -0.08
    å¿ĥåºķ
    -0.08
    è¿Ľé£Ł
    -0.08
    ç«ŀ
    -0.08
    POSITIVE LOGITS
    丧失
    0.10
    丢失
    0.09
    ä¸įåĨį
    0.09
    å²ģæľĪ
    0.09
     Sind
    0.09
    ä¸įåĨįæĺ¯
    0.09
    绡
    0.09
    elder
    0.09
    å¼¹æĢ§
    0.09
    åĢ¾åIJij
    0.08
    Activations Density 0.134%

    No Known Activations