© 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. 39798
    Prev
    Next
    INDEX
    Explanations

    pudding or puddle

    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
    odia
    -0.09
    åıªä¸įè¿ĩ
    -0.09
    宾
    -0.08
    讦
    -0.08
    åIJĮæľŁ
    -0.08
     ев
    -0.08
    åĽĽçº§
    -0.08
    è°®
    -0.08
     Shelley
    -0.08
    æīŃæĽ²
    -0.08
    POSITIVE LOGITS
    ç¥ĵ
    0.09
    çĦ¶æĺ¯
    0.09
    ÑīÑĥ
    0.09
    ANCE
    0.09
    æįħ
    0.09
    empor
    0.08
    allest
    0.08
    idge
    0.08
    ë¡Ń
    0.08
    ERY
    0.08
    Activations Density 0.003%

    No Known Activations