© 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. 57957
    Prev
    Next
    INDEX
    Explanations

    subprime mortgage securities

    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
    èĻ«
    -0.10
    обоÑĢ
    -0.10
    ä¼ı
    -0.10
    èŁ²
    -0.10
    åĴ¸
    -0.09
     ÑģÑĤоим
    -0.09
    åīįéĢĶ
    -0.09
    æ·¡æ°´
    -0.09
    åħļåĴĮåĽ½å®¶
    -0.09
    åħ¨æĻ¯
    -0.09
    POSITIVE LOGITS
    å°ģ
    0.10
    æĤ¬
    0.10
    icle
    0.09
    -backed
    0.09
    äºļè¿IJ
    0.09
     bund
    0.09
    ä¿ĿèįIJ
    0.08
    éĻ¶
    0.08
    åıijåĶ®
    0.08
    9
    0.08
    Activations Density 0.046%

    No Known Activations