© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    phytoplankton and eutrophication

    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¸įæĿ¥
    -0.10
    æľªæĿ¥çļĦ
    -0.10
    æIJ¬è¿ģ
    -0.10
    Bullet
    -0.09
    éĴ½
    -0.09
    æĪķ
    -0.09
    çĶŃ
    -0.09
    æĭĮ
    -0.09
    èŀ«
    -0.09
    饧
    -0.09
    POSITIVE LOGITS
    èĥŀ
    0.09
    _lang
    0.08
    åIJŀ
    0.08
    çī©è´¨
    0.08
    å¯ħ
    0.08
    Submitted
    0.08
    avor
    0.08
    åįķ纯
    0.08
    èijĽ
    0.07
    -corner
    0.07
    Activations Density 0.090%

    No Known Activations