© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    at age or during an event

    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
    é¦Ī
    -0.10
     Äijiá»ĥn
    -0.10
    äºļ
    -0.10
    èĥ¡åŃIJ
    -0.10
    çĮ®
    -0.09
    é¦ı
    -0.09
    缴è¾ĸ
    -0.08
    åºĶä»ĺ
    -0.08
     Dew
    -0.08
    achable
    -0.08
    POSITIVE LOGITS
    ä¸įåĨįæĺ¯
    0.10
    èĩªçĦ¶æĺ¯
    0.09
    èµ
    0.09
     Ø´ÙĬ
    0.08
    æµ·æĭĶ
    0.08
    emaker
    0.08
    å±ħ家
    0.08
    åģļä¸įåĪ°
    0.08
    åħ¬å¯ĵ
    0.08
    åľ¨å®¶éĩĮ
    0.08
    Activations Density 0.020%

    No Known Activations