© 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. 29562
    Prev
    Next
    INDEX
    Explanations

    insect infestation or control

    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
    é»į
    -0.11
    车主
    -0.10
    å¹³åİŁ
    -0.10
    ograms
    -0.10
    èģĶåIJĪ
    -0.10
    æŁ©
    -0.09
    áħŁ
    -0.09
    è¾Ł
    -0.09
    _WEEK
    -0.09
    主èIJ¥ä¸ļ
    -0.09
    POSITIVE LOGITS
    èĻ«
    0.18
    èĽĢ
    0.13
    èŁ²
    0.13
    .att
    0.12
    èĿĩ
    0.11
    èļĬ
    0.11
    èĻ±
    0.10
    èļģ
    0.10
    worm
    0.10
    atten
    0.10
    Activations Density 0.083%

    No Known Activations