© 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. 17869
    Prev
    Next
    INDEX
    Explanations

    university and college names

    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
    acja
    -0.09
     vic
    -0.09
    æ»Ł
    -0.09
    æĪı
    -0.09
    vic
    -0.08
    á»ģn
    -0.08
    viso
    -0.08
     ship
    -0.08
    èĪ¹
    -0.08
    warts
    -0.08
    POSITIVE LOGITS
    æIJŃ
    0.10
    æĩĪ
    0.10
    ä¸ĬéŨ
    0.10
    èĽĭ
    0.10
    pls
    0.09
    Dating
    0.09
    åħļåĨħ
    0.09
    æĹĭ
    0.09
    èī¯å¿ĥ
    0.09
    建åįİ
    0.09
    Activations Density 0.005%

    No Known Activations