© 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. 47676
    Prev
    Next
    INDEX
    Explanations

    boilerplate nautical meanings

    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
    äºĨèĩªå·±çļĦ
    -0.09
    äºĨ大éĩıçļĦ
    -0.09
    åĦ¿
    -0.08
    åı¯çĪ±çļĦ
    -0.08
    稿件
    -0.08
    âĶĮ
    -0.08
     бÑĭ
    -0.08
    åħļæĢ»
    -0.08
    abled
    -0.08
     дог
    -0.08
    POSITIVE LOGITS
    åIJĦçķĮ
    0.09
    stance
    0.09
    çŧ
    0.09
    tery
    0.09
    çĹĩ
    0.09
    aus
    0.09
    å§IJ妹
    0.08
    ilda
    0.08
    åIJĮèĥŀ
    0.08
    libs
    0.08
    Activations Density 0.007%

    No Known Activations