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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20567
    Prev
    Next
    INDEX
    Explanations

    child safety skills

    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
    èij«
    -0.10
    çľŁç©º
    -0.10
    sil
    -0.09
    åĽŀåİ»
    -0.09
    åĮĨåĮĨ
    -0.09
    çĻ¾å®¶
    -0.09
    æī«ä¸Ģ
    -0.08
    æĬ½
    -0.08
    oref
    -0.08
    å½ĵåľ°äºº
    -0.08
    POSITIVE LOGITS
    çĸ¤
    0.11
    å®īåħ¨ç®¡çIJĨ
    0.11
    åĦ¿ç«¥
    0.10
    æľªæĪIJå¹´
    0.10
    .safe
    0.10
    å®īåħ¨
    0.10
    çļĦå®īåħ¨
    0.10
    帽
    0.09
    æĮĩåįĹ
    0.09
    éĴĵé±¼
    0.09
    Activations Density 0.094%

    No Known Activations