© 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. 18716
    Prev
    Next
    INDEX
    Explanations

    by followed by my or our

    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
    åĭī强
    -0.09
    moth
    -0.09
    INGS
    -0.09
    æĪijä¸įçŁ¥éģĵ
    -0.09
    躯
    -0.09
    éĢ¡
    -0.09
     Antar
    -0.09
    ä¸įæŃ»
    -0.09
    ukes
    -0.09
    èĥ³èĨĬ
    -0.09
    POSITIVE LOGITS
    çĨŁæĤīçļĦ
    0.09
    coni
    0.09
    iou
    0.08
    èĩ¾
    0.08
    èĩªçĦ¶èĢĮ
    0.08
    nie
    0.08
    åIJĮä¸Ģ
    0.08
    _serialize
    0.08
    nil
    0.08
    æ±ł
    0.08
    Activations Density 0.007%

    No Known Activations