© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    gift card, voucher, credits

    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
    çªģ
    -0.09
    æĻļæĬ¥
    -0.09
    packed
    -0.09
    assy
    -0.09
    اسÙĬ
    -0.09
     ìĪĺì§ij
    -0.08
    åı
    -0.08
    çªģåĩº
    -0.08
    jen
    -0.08
    æĹĮ
    -0.08
    POSITIVE LOGITS
    åĩłå¼ł
    0.11
    åħħåĢ¼
    0.11
    转åħ¥
    0.10
    åı¯çĶ¨äºİ
    0.10
    注åĨĮèµĦæľ¬
    0.09
    åħ¨åľº
    0.09
    åħij
    0.09
    spb
    0.09
     credits
    0.09
    æĬµ
    0.09
    Activations Density 0.207%

    No Known Activations