© 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. 23767
    Prev
    Next
    INDEX
    Explanations

    sale or buying property

    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
     AppModule
    -0.10
    ä¸Ńå¿ĥåŁİå¸Ĥ
    -0.10
    olv
    -0.09
    奢
    -0.09
    ç§ijæĬĢèĤ¡ä»½
    -0.09
    ë²Į
    -0.09
     armour
    -0.09
    群
    -0.09
    å¦Ĵ
    -0.08
    _FRE
    -0.08
    POSITIVE LOGITS
    转让
    0.18
    åĩºåĶ®
    0.16
    åįĸç»Ļ
    0.13
    åĩºè®©
    0.12
    æīĢæľīæĿĥ
    0.12
    æİ¥æīĭ
    0.12
    åįĸ家
    0.12
    Sale
    0.12
     sale
    0.11
    åįĸæİī
    0.11
    Activations Density 0.131%

    No Known Activations