© 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. 18026
    Prev
    Next
    INDEX
    Explanations

    girl or femininity

    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
    峪
    -0.09
    odzi
    -0.09
    å·ŀ
    -0.09
    å¼ŁåħĦ
    -0.09
    éĺ±
    -0.08
    派人
    -0.08
     lif
    -0.08
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    NIC
    -0.08
    鸷
    -0.08
    POSITIVE LOGITS
    å°ij女
    0.12
    æĶ¾åѦ
    0.10
    âĶĢâĶĢâĶĢâĶĢ
    0.10
     cosplay
    0.10
     Justi
    0.10
     Capcom
    0.09
    anime
    0.09
    害ç¾ŀ
    0.09
    åIJIJ槽
    0.09
     tÃł
    0.09
    Activations Density 0.127%

    No Known Activations