© 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. 60947
    Prev
    Next
    INDEX
    Explanations

    sexual abuse and harassment

    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
     кÑĢÑĥ
    -0.09
     Assass
    -0.09
    åĪĨæīĭ
    -0.09
    ÑĢам
    -0.09
    çľģåħ¬å®īåİħ
    -0.09
    å®ĭ代
    -0.09
    æļ´
    -0.09
    getDefault
    -0.08
    ç¢İçīĩ
    -0.08
    pling
    -0.08
    POSITIVE LOGITS
    ç½ijç»ľä¼łæĴŃ
    0.11
    è¾ħ导
    0.10
    agli
    0.09
    èħ°éĥ¨
    0.09
    伸æīĭ
    0.09
    å¤ļ家
    0.09
    æĬ±ä½ı
    0.09
    igans
    0.09
    æĬļæij¸
    0.09
    æĭĽæĬķæłĩ
    0.09
    Activations Density 0.049%

    No Known Activations