© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49295
    Prev
    Next
    INDEX
    Explanations

    sexual abuse or exploitation

    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
    æŀ¢
    -0.10
    ensch
    -0.10
    å«ģç»Ļ
    -0.10
    å©ļ礼
    -0.09
    ä¸Ī夫
    -0.09
    å¨ĺ家
    -0.09
    çħ§
    -0.09
    UGHT
    -0.09
    ç»ĵå©ļ
    -0.09
    èĢģåħ¬
    -0.08
    POSITIVE LOGITS
    æµ·æ£ł
    0.10
    çļĦä¹łæĥ¯
    0.09
    èĦį
    0.09
    shaw
    0.09
     FAG
    0.09
    ãģ¼
    0.09
    ç»ıéªĮåĢ¼
    0.08
    itian
    0.08
    ä¹łæĥ¯
    0.08
    éĩĩ访
    0.08
    Activations Density 0.092%

    No Known Activations