© 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. 52039
    Prev
    Next
    INDEX
    Explanations

    believe that

    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
    enes
    -0.11
    å°±è¿ij
    -0.11
    born
    -0.11
    é¹ŀ
    -0.09
    orny
    -0.09
     бÑĭ
    -0.09
    åĴ¬
    -0.09
    olis
    -0.09
    æĤŁ
    -0.09
    çİ¢
    -0.09
    POSITIVE LOGITS
     something
    0.11
    ä»Ģä¹Īåij¢
    0.10
    ä»Ģä¹ĪæĦıæĢĿ
    0.10
    æŁIJç§į
    0.09
    以èĩ³äºİ
    0.08
    logen
    0.08
     Bou
    0.08
    æī°
    0.08
     shield
    0.08
    something
    0.08
    Activations Density 0.046%

    No Known Activations