© 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. 33978
    Prev
    Next
    INDEX
    Explanations

    house, car, mortgage, worth

    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
    姹
    -0.09
     eccentric
    -0.09
    å¤ĸ交éĥ¨
    -0.08
    åİĤåĮº
    -0.08
    äºijéĽĨ
    -0.08
    èıĬ
    -0.08
    nder
    -0.08
    orro
    -0.08
    大è¡Ĺ
    -0.08
    çİij
    -0.08
    POSITIVE LOGITS
    è´ŃæĪ¿
    0.16
    ä¹°æĪ¿
    0.16
    çļĦæĪ¿åŃIJ
    0.14
    è´Ńç½®
    0.14
    è´Ń车
    0.13
    æĪ¿åŃIJ
    0.13
    买车
    0.13
    è´Ńä¹°
    0.12
    æĪ¿è´·
    0.12
    ä½ıæĪ¿
    0.12
    Activations Density 0.062%

    No Known Activations