© 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. 7684
    Prev
    Next
    INDEX
    Explanations

    everything I

    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¤©çľŁ
    -0.10
     Enough
    -0.10
    人人
    -0.10
    大家ä¸Ģèµ·
    -0.09
    æĪijå¾Ī
    -0.09
    åŃĺéĩı
    -0.09
    <![
    -0.09
    æĺ¯å¾Ī
    -0.08
    人人éĥ½
    -0.08
    ife
    -0.08
    POSITIVE LOGITS
    except
    0.10
     except
    0.10
    лож
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    éĩijéĵ¶
    0.09
    Except
    0.08
    æ³
    0.08
    upa
    0.08
    åıī
    0.08
     жив
    0.08
    Activations Density 0.027%

    No Known Activations