© 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. 11355
    Prev
    Next
    INDEX
    Explanations

    adjuvant vaccine Covaxis

    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
    illery
    -0.10
    èĤĨ
    -0.09
    otti
    -0.09
    ipers
    -0.09
    å§Ĭ妹
    -0.09
     Burl
    -0.09
    亲å±ŀ
    -0.09
    æ¤į
    -0.09
    ç»´å°Ķ
    -0.09
     ÑģиÑĤ
    -0.08
    POSITIVE LOGITS
    æİ¥ç§į
    0.10
    çĸ«èĭĹ
    0.09
    bery
    0.09
    поÑĢ
    0.09
     Tah
    0.09
    æŀ¯
    0.09
     Fired
    0.09
    天èĬ±
    0.09
    EMON
    0.08
    akh
    0.08
    Activations Density 0.174%

    No Known Activations