© 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. 4072
    Prev
    Next
    INDEX
    Explanations

    sex determination

    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
    çĥĽ
    -0.09
    eker
    -0.09
    åIJ¾
    -0.09
    atron
    -0.09
    æĬĺ
    -0.08
     pä
    -0.08
    ä¸ĢæĹ¥
    -0.08
    ijn
    -0.08
     Mate
    -0.08
    _NB
    -0.08
    POSITIVE LOGITS
    çĶ·åŃ©
    0.14
    åĦ¿å¥³
    0.12
    æĢ§åĪ«
    0.11
    好äºĭ
    0.11
    æµģåĩº
    0.10
    çĶ·åŃ©åŃIJ
    0.10
    å°ıé¾Ļ
    0.10
    女åĦ¿
    0.10
     boys
    0.10
    女
    0.10
    Activations Density 0.078%

    No Known Activations