© 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. 8033
    Prev
    Next
    INDEX
    Explanations

    County, Haram, Perry, Tarrant

    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
     coins
    -0.10
     Coins
    -0.09
    rieve
    -0.09
    寥
    -0.09
    åĮĹ约
    -0.09
    ä¼łæŁĵ
    -0.09
    åĴ§
    -0.08
    Coins
    -0.08
    ettel
    -0.08
    åī¯æľ¬
    -0.08
    POSITIVE LOGITS
    beiten
    0.10
    éŃĶ鬼
    0.09
    oders
    0.09
    liness
    0.09
     Summers
    0.09
    é³Į
    0.09
    ible
    0.09
    红èī²
    0.09
    裸
    0.08
    .reload
    0.08
    Activations Density 0.001%

    No Known Activations