© 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. 37344
    Prev
    Next
    INDEX
    Explanations

    studio or labs

    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
    åİ¿åħ¬å®īå±Ģ
    -0.09
    æ§Ĭ
    -0.09
    CORD
    -0.09
    instanc
    -0.09
    å¸Įå°Ķ
    -0.09
    ë²Īíĺ¸
    -0.09
    嵬
    -0.08
    earch
    -0.08
    æ²³æµģåŁŁ
    -0.08
    éĻĮçĶŁäºº
    -0.08
    POSITIVE LOGITS
    äºİæĺ¯æĪij
    0.10
    æĹĹä¸ĭ
    0.09
    æĹĹä¸ĭçļĦ
    0.09
    翳
    0.09
    åĩºåĵģ
    0.09
    æķĻä½ł
    0.09
    é¢Ĩè¢ĸ
    0.09
    åīĬ
    0.08
    å¨ĺ
    0.08
    èĪ«
    0.08
    Activations Density 0.028%

    No Known Activations