© 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. 38982
    Prev
    Next
    INDEX
    Explanations

    author or press

    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
    dit
    -0.08
     Lover
    -0.08
    æ»´æ»´
    -0.08
    ä»İåīį
    -0.08
     Minerals
    -0.08
    人åĿĩ
    -0.07
    æķĻçłĶ
    -0.07
    æĬķè¯ī
    -0.07
     +#+
    -0.07
    entr
    -0.07
    POSITIVE LOGITS
    æĤ±
    0.10
    æĤ²åĵĢ
    0.10
    æĥ³çŁ¥éģĵ
    0.09
    ä½ľèĢħ
    0.09
    pies
    0.09
    å£ħ
    0.08
    æľ¬æĸĩ
    0.08
    笨
    0.08
    æŁ¥æĺİ
    0.08
    visor
    0.08
    Activations Density 0.021%

    No Known Activations