© 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. 17684
    Prev
    Next
    INDEX
    Explanations

    a new, brief, sentence, little, sneak

    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
    çħŀ
    -0.11
    è¿Ļç§įäºĭæĥħ
    -0.10
    åĿ»
    -0.10
    æ¯ıä¸Ģ次
    -0.10
    è¿Ļä¹Īåģļ
    -0.10
    游æĪıå½ĵä¸Ń
    -0.10
    è¾ĸåĮºåĨħ
    -0.10
    è¿Ļæł·åģļ
    -0.10
    ows
    -0.09
    è·
    -0.09
    POSITIVE LOGITS
    alus
    0.09
    alink
    0.08
     Honest
    0.08
    LIN
    0.08
     link
    0.08
    2
    0.08
    umont
    0.07
    بÙĪÙĨ
    0.07
    uo
    0.07
    ^^^^
    0.07
    Activations Density 0.040%

    No Known Activations