© 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. 1806
    Prev
    Next
    INDEX
    Explanations

    selling or buying homes

    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
    å·¥ä½ľæľºåĪ¶
    -0.09
    翼
    -0.09
    esses
    -0.08
    lass
    -0.08
    è¾Ł
    -0.08
    ardi
    -0.08
     Nab
    -0.08
    ìĪł
    -0.08
     overflowing
    -0.08
     Pon
    -0.07
    POSITIVE LOGITS
    买家
    0.13
    åįĸ家
    0.12
     Seller
    0.10
     Buyer
    0.10
    buyer
    0.10
    æĢ¥äºİ
    0.10
     buyer
    0.10
     Buyers
    0.10
    lys
    0.09
    åīįä»»
    0.09
    Activations Density 0.206%

    No Known Activations