© 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. 56127
    Prev
    Next
    INDEX
    Explanations

    looks like

    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
    çłĶ究表æĺİ
    -0.09
    åĩĨç¡®æĢ§
    -0.09
    æľīæķĪæĢ§
    -0.09
    身é«ĺ
    -0.09
    èĩªä¿¡
    -0.09
    aghan
    -0.09
    å¹³åı°ä¸Ĭ
    -0.09
    ании
    -0.09
    äºĨ大éĩıçļĦ
    -0.09
    æ·®åįĹ
    -0.09
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.12
    ãģŁãģł
    0.09
     something
    0.09
    SES
    0.09
    è¿Ļæł·æīįèĥ½
    0.08
    ucher
    0.08
    omething
    0.08
    /is
    0.08
     nothing
    0.08
    CES
    0.08
    Activations Density 0.025%

    No Known Activations