© 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. 58455
    Prev
    Next
    INDEX
    Explanations

    per unit of time/person

    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
    etz
    -0.09
    æĭ£
    -0.09
    æı
    -0.08
    æį¡
    -0.08
    	sn
    -0.08
    æĥķ
    -0.08
    QueryBuilder
    -0.08
    .Addr
    -0.08
    éĻįèIJ½
    -0.08
    mue
    -0.08
    POSITIVE LOGITS
    人åĿĩ
    0.19
    æ¯ı人
    0.18
    æ¯ı个人çļĦ
    0.15
    æ¯ı个人
    0.15
    æ¯ıä½į
    0.14
    ä¸Ģ人
    0.12
    年人
    0.12
    å¹³åĿĩ
    0.11
    æ¯ıä¸Ģ个人
    0.10
     per
    0.10
    Activations Density 0.043%

    No Known Activations