© 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. 40042
    Prev
    Next
    INDEX
    Explanations

    children, kids, or adult animated content

    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
    æĻļ
    -0.09
    ä¸ĢèĪ¬äºº
    -0.09
    临
    -0.09
    å¤ĸåľ°
    -0.09
    åľ¨ä»Ĭå¹´
    -0.09
    åIJĬ
    -0.09
    çļĦ人æĿ¥è¯´
    -0.08
    æį
    -0.08
    OTA
    -0.08
    mdb
    -0.08
    POSITIVE LOGITS
    æ²ħ
    0.10
    åĦ¿ç«¥
    0.10
    娱
    0.10
    好çİ©
    0.09
     regress
    0.09
     Ages
    0.09
    åħij
    0.09
    糧
    0.09
    STACK
    0.09
    æķ£çĥŃ
    0.09
    Activations Density 0.128%

    No Known Activations