© 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. 51143
    Prev
    Next
    INDEX
    Explanations

    closing or exiting

    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»ĸèĩªå·±
    -0.08
     Sham
    -0.08
    çī¹çĤ¹æĺ¯
    -0.08
    ä¼łè¯´
    -0.08
    Aqu
    -0.08
    ç»į
    -0.08
    ç»ıåİĨè¿ĩ
    -0.08
    åĿļå®ļä¸į移
    -0.08
     rec
    -0.08
    ron
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.10
    dealloc
    0.10
    .jd
    0.09
    çŀ¢
    0.09
    éĹ¾
    0.09
    å¿ĥä¸ŃçļĦ
    0.09
    âľĭ
    0.09
    âĺ°
    0.08
    .Free
    0.08
    wend
    0.08
    Activations Density 0.071%

    No Known Activations