© 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. 61575
    Prev
    Next
    INDEX
    Explanations

    Chevrolet vehicles

    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
    uliar
    -0.11
    aiser
    -0.10
    èĪ¶
    -0.10
    ä¾ł
    -0.10
    esis
    -0.10
    -flash
    -0.09
    orent
    -0.09
    æķijåij½
    -0.09
    zzo
    -0.09
    æĻ®æĥł
    -0.09
    POSITIVE LOGITS
    侬
    0.10
    ÙĦÙĤ
    0.09
    ÑĤе
    0.09
    izable
    0.09
    ÇĴ
    0.09
    æľīä¸įå°ij
    0.09
    ä¸įåģľ
    0.08
    æĹłçĸij
    0.08
    gren
    0.08
    æľīä¸Ģ次
    0.08
    Activations Density 0.005%

    No Known Activations