© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51515
    Prev
    Next
    INDEX
    Explanations

    try again

    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
    å¤ļåħĥ
    -0.10
    æ®ĭ
    -0.09
    .DOWN
    -0.09
    lis
    -0.09
    æľ¬ç½ij
    -0.08
    phinx
    -0.08
    croft
    -0.08
    ibilities
    -0.08
    ALA
    -0.08
    å¦Ĥå®ŀ
    -0.08
    POSITIVE LOGITS
    æĻ¶
    0.09
    ä¸Ģéģį
    0.09
    ä¸ĩ人
    0.08
    å¸ĤåĢ¼
    0.08
    å±ĢéĿ¢
    0.08
    äºĨä¸Ģéģį
    0.08
    æİ¥è¿ij
    0.08
    ä¸įè¿ľå¤Ħ
    0.08
    å°±è¿ij
    0.08
     Proud
    0.08
    Activations Density 0.023%

    No Known Activations