© 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. 11787
    Prev
    Next
    INDEX
    Explanations

    female names or attributes

    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
    æ¸ħç®Ĺ
    -0.10
    izu
    -0.09
    ECT
    -0.09
    Tpl
    -0.09
    å°ıé¾Ļ
    -0.09
    riv
    -0.09
    éra
    -0.09
    ITOR
    -0.09
    (quantity
    -0.09
    篱
    -0.09
    POSITIVE LOGITS
    æĺİæĺŁ
    0.13
    代è¨Ģ
    0.12
     fans
    0.11
    å·¨æĺŁ
    0.11
    çIJĥæĺŁ
    0.11
    æ¼Ķ
    0.10
    ç²īä¸Ŀ
    0.10
    ç»Ļä½łä»¬
    0.10
    èīºäºº
    0.10
    çŃ¾åIJį
    0.10
    Activations Density 0.099%

    No Known Activations