© 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. 9105
    Prev
    Next
    INDEX
    Explanations

    attributions after punctuation

    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
    槲
    -0.09
    Äı
    -0.08
    Unnamed
    -0.08
    æķ£åıijçĿĢ
    -0.08
    arness
    -0.08
    çļĦ羣å®ŀæĢ§
    -0.08
    é¢Ķ
    -0.08
    éĴĿ
    -0.08
    æĺĢ
    -0.08
    afari
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.13
    æĸ©
    0.11
    åIJĮæĹ¶ä¹Łæĺ¯
    0.10
    ëĭĺ
    0.10
    èªĵ
    0.09
    oire
    0.09
     ê²
    0.09
    .gf
    0.09
    æѤäºĭ
    0.09
    pig
    0.09
    Activations Density 0.105%

    No Known Activations