© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8189
    Prev
    Next
    INDEX
    Explanations

    software inc

    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
     ÐŁÐµÑĢе
    -0.09
    è¾ħ
    -0.09
     braz
    -0.09
     Whites
    -0.08
    iram
    -0.08
    涪
    -0.08
    éļĺ
    -0.08
    è¼Ķ
    -0.08
    寸
    -0.08
     Fernando
    -0.08
    POSITIVE LOGITS
    åŃĿ
    0.09
    çī§
    0.09
    端æŃ£
    0.08
     homeschool
    0.08
    绣çŃ¹
    0.08
    åĿļ硬
    0.08
    åħ¨æĹ¥
    0.08
    çĬ¬
    0.08
    骨æŀ¶
    0.08
    åı¸
    0.08
    Activations Density 0.059%

    No Known Activations