© 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. 31235
    Prev
    Next
    INDEX
    Explanations

    grades A or A-

    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
    ä¸įäºĨ
    -0.10
    THEN
    -0.09
    /UI
    -0.09
    ingu
    -0.08
     aggregator
    -0.08
    eri
    -0.08
    cher
    -0.08
    è½°
    -0.08
    ä¸Ģå¤Ħ
    -0.08
    erus
    -0.08
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
    è´¨éĩıåĴĮ
    0.10
    æł·çļĦ
    0.10
    èĪ¬
    0.09
    以ä¸ĬçļĦ
    0.09
    AGR
    0.09
    emd
    0.08
    梯éĺŁ
    0.08
    èİł
    0.08
    åľ°åĮº
    0.08
    Activations Density 0.023%

    No Known Activations