© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7284
    Prev
    Next
    INDEX
    Explanations

    farmers market

    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
    çĪ·
    -0.11
    oso
    -0.10
    less
    -0.09
    око
    -0.08
    Explorer
    -0.08
     Recommend
    -0.08
    ombat
    -0.08
     обо
    -0.08
     Gund
    -0.08
    frauen
    -0.08
    POSITIVE LOGITS
    管å§Ķä¼ļ
    0.11
    ien
    0.09
    onne
    0.09
    çĿ¨
    0.08
    åŃ£
    0.08
    [sub
    0.08
    æĶ¹éĿ©åıijå±ķ
    0.08
    俪
    0.08
    è¯ı
    0.08
    è¿IJèIJ¥åķĨ
    0.08
    Activations Density 0.003%

    No Known Activations