© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51872
    Prev
    Next
    INDEX
    Explanations

    place names ending in stown or burg

    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
    lide
    -0.11
    å¼ĢæĶ¾å¼ı
    -0.09
    羣çĪ±
    -0.09
    бил
    -0.09
    ProcessEvent
    -0.09
    åIJİèĢħ
    -0.09
    igy
    -0.09
    лад
    -0.09
    éĩijåŃĹ
    -0.09
    èĩ³ä¸Ĭ
    -0.09
    POSITIVE LOGITS
    elves
    0.10
    _ca
    0.09
     Ca
    0.09
    æĿŀ
    0.09
    ungs
    0.09
    ém
    0.08
    åħľ
    0.08
    è°§
    0.08
    oret
    0.08
    orus
    0.08
    Activations Density 0.001%

    No Known Activations