© 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. 4379
    Prev
    Next
    INDEX
    Explanations

    licensing agreements and commercial rights

    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
    票
    -0.10
    éĢĴ交
    -0.09
    åĮ¹
    -0.09
    çŃ¹
    -0.09
    phia
    -0.09
     Haz
    -0.09
    erot
    -0.09
    Äĺ
    -0.09
    PropertyName
    -0.09
    PTH
    -0.09
    POSITIVE LOGITS
    icle
    0.10
    åĪ»
    0.09
    å¸ĪèĮĥ
    0.09
    éģĭçĶ¨
    0.09
     royalties
    0.08
    å´ĩ
    0.08
    å¼ĭ
    0.08
     Sour
    0.08
    享
    0.08
    è´¡
    0.08
    Activations Density 0.050%

    No Known Activations