© 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. 55730
    Prev
    Next
    INDEX
    Explanations

    after which

    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
    éĤ£å°±æĺ¯
    -0.10
    å°±æĺ¯è¿Ļæł·
    -0.10
    ä¸īæľŁ
    -0.10
    åĴĮåľ°åĮº
    -0.10
    å°±è¿Ļæł·
    -0.09
    åģıåģı
    -0.09
    å·½
    -0.09
    åŀ¦
    -0.09
    å°±è¿Ļä¹Ī
    -0.09
    æĹ¥æĬ¥è®°èĢħ
    -0.09
    POSITIVE LOGITS
    æŶéĹ´åĨħ
    0.09
    满æĦıçļĦ
    0.08
    ness
    0.08
    满æĦı
    0.08
    COPY
    0.08
    GBT
    0.08
    quelle
    0.08
    asti
    0.08
    æĪijçļĦå¿ĥ
    0.07
    ORTH
    0.07
    Activations Density 0.042%

    No Known Activations