© 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. 35703
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ull
    -0.09
    ally
    -0.09
    æľĪä¸ĭ
    -0.09
    妥
    -0.08
    ly
    -0.08
    ogi
    -0.08
    umer
    -0.08
    çIJĨ解åĴĮ
    -0.08
    ulated
    -0.08
    ULL
    -0.08
    POSITIVE LOGITS
    å¿«æĬ¥
    0.11
    à¹Ģลย
    0.09
    ERING
    0.09
    пÑĢÑı
    0.09
    两边
    0.09
    егод
    0.09
    çļĦç¨ĭ度
    0.09
    utral
    0.09
    chin
    0.09
     roy
    0.09
    Activations Density 0.000%

    No Known Activations