© 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. 30444
    Prev
    Next
    INDEX
    Explanations

    seeing or hearing about something

    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
    åµĩ
    -0.09
    ame
    -0.09
    趣
    -0.08
    à¹ģห
    -0.08
    æĦīå¿«
    -0.08
    å¾Ĺ以
    -0.08
    ument
    -0.08
    说åĪ°
    -0.08
     componentWill
    -0.08
    æĦıè¯Ĩ
    -0.08
    POSITIVE LOGITS
    æīįçŁ¥éģĵ
    0.10
    èĪ¶
    0.10
    èĨĬ
    0.09
     fellow
    0.09
    翱
    0.09
    è¿Ļç¯ĩ
    0.09
    并ä¸İ
    0.09
    æĪijçļĦå¿ĥ
    0.09
    è²Į
    0.08
    æĴij
    0.08
    Activations Density 0.033%

    No Known Activations