© 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. 2570
    Prev
    Next
    INDEX
    Explanations

    marriage and union types

    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
    èĮĦ
    -0.11
    маÑĢ
    -0.11
     jerk
    -0.10
    éªĪ
    -0.09
    沮丧
    -0.09
    èĬĭ
    -0.09
     jer
    -0.09
    åŁİå¸Ĥ建设
    -0.09
    åıĤèµĽ
    -0.09
    çķĻä¸ĭäºĨ
    -0.09
    POSITIVE LOGITS
    çĶ·å¥³
    0.10
    ç»ĵ
    0.10
     оÑĤноÑĪениÑı
    0.10
     Rak
    0.10
    ohana
    0.09
    Ñģан
    0.09
     ÑĤоÑĢ
    0.09
    furt
    0.08
    æ¡ij
    0.08
    æ®ĸ
    0.08
    Activations Density 0.039%

    No Known Activations