© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10182
    Prev
    Next
    INDEX
    Explanations

    rental properties or prices

    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
    嵬
    -0.09
    è®°èĢħéĩĩ访
    -0.08
    å·ŀåĮº
    -0.08
    æīijåħĭ
    -0.08
    ãģ»ãģĨ
    -0.08
    å¥ij
    -0.08
     Welsh
    -0.08
    åIJ¦è®¤
    -0.08
    ä¸Ģ缴
    -0.08
    Ùħج
    -0.07
    POSITIVE LOGITS
    asti
    0.09
     Bates
    0.09
    æĽ´ä½ķåĨµ
    0.09
    åºĶä»ĺ
    0.09
     Nurs
    0.09
     Knights
    0.08
    ä¸į该
    0.08
     Shim
    0.08
    æĹ¥åŃIJ
    0.08
    æ¡£
    0.08
    Activations Density 0.004%

    No Known Activations