© 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. 61221
    Prev
    Next
    INDEX
    Explanations

    at least

    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
    ä¸įä½Ĩ
    -0.10
    åħ¶å¯¦
    -0.10
    éĮĦ
    -0.09
    å½ķ
    -0.09
    ymax
    -0.09
    æĹ¢æĺ¯
    -0.09
    ãģĿãĤĤãģĿãĤĤ
    -0.09
    åijĽ
    -0.09
    åħ¶å®ŀæĺ¯
    -0.08
    竦
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.10
    æĪijæĺ¯
    0.09
    个人è§ĤçĤ¹
    0.09
    éĤ£äºĽ
    0.09
    åľ¨æĪij
    0.09
    æĪijåľ¨
    0.09
    oire
    0.09
    olas
    0.09
     ones
    0.08
    è¿Ļæĺ¯æĪij
    0.08
    Activations Density 0.009%

    No Known Activations