© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10038
    Prev
    Next
    INDEX
    Explanations

    evacuate or shut down

    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
    éĻĢ
    -0.10
    pio
    -0.09
    _tm
    -0.08
     sec
    -0.08
    ä¹°åĪ°
    -0.08
    å¢ĥ
    -0.08
    .addTab
    -0.08
    olly
    -0.08
    indent
    -0.07
    ATUS
    -0.07
    POSITIVE LOGITS
    纷纷
    0.10
    æĤ¬
    0.10
    æµij
    0.10
    æłĭ
    0.10
    ç¥ŀèī²
    0.09
    åľ¨æİ¥åıĹ
    0.09
    æĸĩä½ĵ
    0.09
     preca
    0.09
    éĩijèī²
    0.09
    宵
    0.09
    Activations Density 0.057%

    No Known Activations