© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29595
    Prev
    Next
    INDEX
    Explanations

    amounts, price, RAM, salary, loan

    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
    Negative Logits
    çŃīå·¥ä½ľ
    -0.09
    åĩŃåĢŁçĿĢ
    -0.08
    çī©æĸĻ
    -0.08
    修身
    -0.08
    æīĵæī®
    -0.08
    zia
    -0.08
     Notices
    -0.08
    ä¸Ģä½ĵ
    -0.07
     Earn
    -0.07
    -end
    -0.07
    POSITIVE LOGITS
    å½ĵæŶ
    0.10
    çķ¶æĻĤ
    0.10
    æľ¬èº«
    0.09
    æijĦ
    0.09
    åħ¨ç¨ĭ
    0.09
    éŁŃ
    0.09
    å½ĵæŶçļĦ
    0.09
    æĪijå½ĵæŶ
    0.08
    å±ĬæŶ
    0.08
    å®ŀéĻħ
    0.08
    Activations Density 0.100%

    No Known Activations