© 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. 18259
    Prev
    Next
    INDEX
    Explanations

    real estate locations and structures

    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
    é©´
    -0.09
    寥
    -0.08
    éļĶ
    -0.08
    çīĴ
    -0.08
    åľºéĿ¢
    -0.08
    æĻķ
    -0.08
    /conf
    -0.08
    å¹ķ
    -0.08
    éĹ´éļĶ
    -0.08
    å®ģ
    -0.08
    POSITIVE LOGITS
    åİŁæľ¬
    0.12
    æĺĶæĹ¥
    0.10
    åİŁåħĪ
    0.10
    hei
    0.10
    åİŁæĿ¥
    0.09
     previously
    0.09
     formerly
    0.09
    æĽ´éĢĤåIJĪ
    0.09
    缮åīįæŃ£åľ¨
    0.09
    å·´å·´
    0.09
    Activations Density 0.075%

    No Known Activations