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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18612
    Prev
    Next
    INDEX
    Explanations

    banned, barred, forbad, prohibits

    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
    ä¸įåģľçļĦ
    -0.10
    æ³¢çī¹
    -0.10
    åĨ¤
    -0.10
    alach
    -0.09
    ä¸Ģå°ģ
    -0.09
     borderline
    -0.09
    GINE
    -0.09
    ä¿Ĺè¯Ŀ说
    -0.09
    ree
    -0.08
    essim
    -0.08
    POSITIVE LOGITS
    éĶ¢
    0.12
    ä¼ģ
    0.09
    æĪĸèĢħ说
    0.09
    许
    0.09
     пÑĢименениÑı
    0.08
     altogether
    0.08
     khá»ıi
    0.08
    _lazy
    0.08
    çĶ¨åĵģ
    0.08
    ä»»ä½ķ人
    0.08
    Activations Density 0.043%

    No Known Activations