© 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. 32134
    Prev
    Next
    INDEX
    Explanations

    river and shipping

    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
    ogn
    -0.10
    รà¸ģ
    -0.10
    æĬ«
    -0.10
    å²Ľä¸Ĭ
    -0.09
     Town
    -0.09
    åį§å®¤
    -0.09
    avana
    -0.09
     Ramirez
    -0.09
    çijŀ
    -0.09
    fried
    -0.09
    POSITIVE LOGITS
    èĪªè¿IJ
    0.10
    轩
    0.08
    伤
    0.08
     maiden
    0.08
     div
    0.08
    å¤Ķ
    0.08
    èĪªçº¿
    0.08
    èĥª
    0.08
    _stage
    0.08
    .ld
    0.08
    Activations Density 0.075%

    No Known Activations