© 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. 18594
    Prev
    Next
    INDEX
    Explanations

    his or her / he or she

    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
    次
    -0.10
    åĸĩåıŃ
    -0.10
    ivos
    -0.09
    ç¨
    -0.09
    åĽŀ头
    -0.09
    åĪĨæµģ
    -0.08
    çī¹å®ļ
    -0.08
    ä½Ĩä¹Ł
    -0.08
    åĮĸåѦåĵģ
    -0.08
    请大家
    -0.08
    POSITIVE LOGITS
    /her
    0.13
    /th
    0.11
    quip
    0.09
    å¸ĤæĶ¿åºľ
    0.08
     Majesty
    0.08
    ÙĨص
    0.08
     ByVal
    0.08
    lando
    0.08
    è´¢æĶ¿
    0.08
    ä¸Ģè½®
    0.08
    Activations Density 0.011%

    No Known Activations