© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53139
    Prev
    Next
    INDEX
    Explanations

    dinosaur extinction era and fossils

    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
    åĽĽåŃ£
    -0.10
    odem
    -0.10
    .Groups
    -0.09
    Reaction
    -0.09
    .SOCK
    -0.09
    åģİ
    -0.09
    çĤ¸å¼¹
    -0.09
    utra
    -0.09
    羣çIJĨ
    -0.09
    åı¸
    -0.08
    POSITIVE LOGITS
    éģĹåĿĢ
    0.09
    çĵ®
    0.09
    åĮĸçŁ³
    0.09
    è¾ĩ
    0.09
    浩
    0.09
    骨æŀ¶
    0.08
    å°±åĮ»
    0.08
    åĴİ
    0.08
    éģĹ迹
    0.08
    éļĨ
    0.08
    Activations Density 0.034%

    No Known Activations