© 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. 47983
    Prev
    Next
    INDEX
    Explanations

    cases are complex

    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
    æŀģéĢŁ
    -0.09
    é«ĺéĢŁå¢ŀéķ¿
    -0.09
     augmentation
    -0.08
    纯åĩĢ
    -0.08
    æŀģ端
    -0.08
     sharp
    -0.08
    æŀģåħ¶
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
     youngest
    -0.08
    TestClass
    -0.08
    POSITIVE LOGITS
    ä¸ĢçĤ¹åĦ¿
    0.11
    enia
    0.10
    æĽ´å¤§
    0.10
    æĽ´å¤§çļĦ
    0.10
    ãģªãĤĤãģ®
    0.10
    æ¶ī
    0.10
    æĮĩ
    0.10
    æ¶īåıĬåĪ°
    0.10
    éľĢè¦ģçĶ¨åĪ°
    0.10
    çĶļèĩ³æĺ¯
    0.09
    Activations Density 0.191%

    No Known Activations