© 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. 34136
    Prev
    Next
    INDEX
    Explanations

    desert emptiness nothing remote

    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
     incumb
    -0.09
    ä¿Ĺ
    -0.09
    訴
    -0.08
    æĭĸæ¬ł
    -0.08
    ris
    -0.08
    èĹı
    -0.08
    urg
    -0.08
    å¿«æĬ¥
    -0.08
    èº²åľ¨
    -0.08
    ade
    -0.08
    POSITIVE LOGITS
    èįĴ
    0.17
    æĹ·
    0.13
    空
    0.13
    åĥ»
    0.11
    æĹłäºº
    0.11
    (empty
    0.11
     desert
    0.11
    æ²Ļæ¼ł
    0.10
    èĮº
    0.10
    .Empty
    0.10
    Activations Density 0.071%

    No Known Activations