© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37266
    Prev
    Next
    INDEX
    Explanations

    day or week references

    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°ıå¿ĥ
    -0.10
     Aust
    -0.10
    é¹Ħ
    -0.09
    çĤĻ
    -0.09
    å®ı
    -0.09
    æĢ»ä½ĵ
    -0.09
    æĶ¶åĪ°äºĨ
    -0.09
    æīįç®Ĺ
    -0.09
    lain
    -0.09
     Rout
    -0.09
    POSITIVE LOGITS
    åij¨åħŃ
    0.11
    礼æĭľ
    0.09
    åı¤äºº
    0.09
    éĺĸ
    0.09
    ä¸ĥ
    0.09
    å¤ļæł·åĮĸ
    0.09
     sunday
    0.08
    å½Ĵ纳
    0.08
    æĺŁæľŁ
    0.08
    涤
    0.08
    Activations Density 0.050%

    No Known Activations