© 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. 54673
    Prev
    Next
    INDEX
    Explanations

    initials followed by periods

    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
    åĭĥ
    -0.09
    ivo
    -0.09
    agal
    -0.08
    åįĵ
    -0.08
    lya
    -0.08
    èĢħçļĦ
    -0.08
     ìĭľ
    -0.08
    usu
    -0.08
    ~~~~~~~~
    -0.08
    æĦıæĢĿ
    -0.08
    POSITIVE LOGITS
    éĹ®éĹ®
    0.10
    塬
    0.09
    åĨł
    0.09
    çļĦ空éĹ´
    0.09
    ä½ĵéĩį
    0.09
    è´¯
    0.08
    ä¸įå°ı
    0.08
    æĤ¬æµ®
    0.08
     crow
    0.08
    VAS
    0.08
    Activations Density 0.031%

    No Known Activations