© 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. 37260
    Prev
    Next
    INDEX
    Explanations

    sexual orientation terms

    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
    åĽŀäºĭ
    -0.09
    aby
    -0.08
    æĬĽå¼ĥ
    -0.08
    对ç«ĭ
    -0.08
    è¡ĮæĶ¿æī§æ³ķ
    -0.08
    æŶè£ħ
    -0.08
    iscrim
    -0.08
    วà¸Ķ
    -0.08
    round
    -0.08
    ayo
    -0.08
    POSITIVE LOGITS
    èĨ
    0.10
     POT
    0.09
    åIJİæĿ¥
    0.09
    éĹ´æİ¥
    0.09
    ä¼łå¯¼
    0.09
    onom
    0.08
    寻
    0.08
    enger
    0.08
     Emblem
    0.08
    alth
    0.08
    Activations Density 0.006%

    No Known Activations