© 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. 35564
    Prev
    Next
    INDEX
    Explanations

    family and home support

    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
    ogan
    -0.09
    çijľ
    -0.09
    çĶ·çĶŁ
    -0.08
     yön
    -0.08
     retreat
    -0.08
    夯
    -0.08
     Retreat
    -0.08
    åĬŀåħ¬å®¤
    -0.08
     Retirement
    -0.08
    (cur
    -0.08
    POSITIVE LOGITS
    ä¸Ģ家人
    0.11
    æĮ£æīİ
    0.11
    社ä¼ļä¿Ŀéļľ
    0.11
    家éĩĮ
    0.10
    ahr
    0.10
    夹
    0.09
    åĭī强
    0.09
    åıªä¸º
    0.09
    ä½İä¿Ŀ
    0.09
    åħ¨å®¶
    0.08
    Activations Density 0.062%

    No Known Activations