© 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. 47759
    Prev
    Next
    INDEX
    Explanations

    minority communities and their advocates

    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¸įè¿ľ
    -0.10
    泡
    -0.10
    rets
    -0.09
    hell
    -0.09
    neau
    -0.09
    walls
    -0.09
    å¹³æ°ij
    -0.09
    æķ´ä¸ªäºº
    -0.08
    лег
    -0.08
    ãģ£ãģį
    -0.08
    POSITIVE LOGITS
    çĭ¬æľīçļĦ
    0.11
    åIJĮèĥŀ
    0.10
    å°Ĭ严
    0.10
    éħĭ
    0.09
    èĩªè±ª
    0.09
    iesen
    0.09
    èĹľ
    0.09
    èŁł
    0.09
    èݼ
    0.09
    eus
    0.09
    Activations Density 0.120%

    No Known Activations