© 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. 55183
    Prev
    Next
    INDEX
    Explanations

    film titles and awards

    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
    以人为
    -0.10
    Lux
    -0.09
    ä¼ĹæīĢ
    -0.09
    路人
    -0.09
    æĶ¯
    -0.09
     çalÄ±ÅŁan
    -0.08
    å¼¢
    -0.08
    éī´åĪ«
    -0.08
     Thousand
    -0.08
    è¿Ļ件
    -0.08
    POSITIVE LOGITS
    æľ¬ç§ij
    0.10
    phere
    0.09
    idade
    0.09
    chaft
    0.09
    illage
    0.09
    Ñģком
    0.09
    olders
    0.08
    idity
    0.08
    иÑĤеÑĤ
    0.08
    对åħ¶çľŁå®ŀ
    0.08
    Activations Density 0.002%

    No Known Activations