© 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. 56488
    Prev
    Next
    INDEX
    Explanations

    dog owners

    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
    ä¸ĩæĪ·
    -0.10
    åħľ
    -0.09
    å©´
    -0.09
    bast
    -0.09
    饶
    -0.08
    æĭ¼éŁ³
    -0.08
    çıIJ
    -0.08
    orno
    -0.08
    没æĥ³åĪ°
    -0.08
    æľĢ常è§ģçļĦ
    -0.08
    POSITIVE LOGITS
    een
    0.09
    iets
    0.09
    èİ«æĸ¯
    0.09
    æ¿ĢåĬ±
    0.09
    keit
    0.08
    ç©·
    0.08
    SENT
    0.08
    å¿ĥå¾Ĺä½ĵä¼ļ
    0.08
    åIJįåı«
    0.08
    æĢ»å±Ģ
    0.08
    Activations Density 0.022%

    No Known Activations