© 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. 32220
    Prev
    Next
    INDEX
    Explanations

    health conditions and therapies

    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
     пок
    -0.09
    æķijåij½
    -0.09
    åģľçķĻ
    -0.09
     sacrific
    -0.08
    insky
    -0.08
    åı£è¢ĭ
    -0.08
    çģ«èĬ±
    -0.08
    åģļæ³ķ
    -0.08
    è¡£
    -0.08
    à¸Ľà¸²à¸ģ
    -0.08
    POSITIVE LOGITS
    产èĥ½
    0.10
    æĭ©
    0.09
    eness
    0.08
    ãĤ«ãĥĥãĥĹ
    0.08
    æĭĽåķĨå¼ķèµĦ
    0.08
    åĩ«
    0.08
     bir
    0.08
    lix
    0.08
    æĺ¯éĿŀ
    0.08
    çļĦåĬ¨åĬĽ
    0.08
    Activations Density 0.095%

    No Known Activations