© 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. 34451
    Prev
    Next
    INDEX
    Explanations

    shipping label transfer systems

    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
    omics
    -0.10
    Æ¡
    -0.09
    æī©å»º
    -0.09
    -org
    -0.09
    æŀ¶æŀĦ
    -0.09
    äºı
    -0.09
    æī©å®¹
    -0.09
    Æł
    -0.08
    Apis
    -0.08
    rush
    -0.08
    POSITIVE LOGITS
    ç©Ĩ
    0.11
    æīĵåĩº
    0.10
    è§ĦåĪĴ建设
    0.10
    çķĮéĻIJ
    0.09
    è®·
    0.09
    æłĩçŃ¾
    0.09
    åĴĴ
    0.09
    绣ä¸Ģ
    0.09
    æīĵ
    0.09
    è´´
    0.09
    Activations Density 0.098%

    No Known Activations