© 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. 17496
    Prev
    Next
    INDEX
    Explanations

    age groups and demographics

    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
    å¥ij
    -0.10
    brush
    -0.09
    $log
    -0.09
    upy
    -0.09
    /stretch
    -0.09
    大åıij
    -0.09
    乡éķĩ
    -0.09
    ãģ¾ãģ¨ãĤģ
    -0.08
    ACHI
    -0.08
    趣
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ段
    0.12
    年纪
    0.11
    å®ľ
    0.11
    çļĦ年轻人
    0.11
    åģ¥
    0.10
    壮
    0.09
    é¾Ħ
    0.09
    éĿĴå¹´
    0.09
    å¹´è½»çļĦ
    0.09
    çĶŁäº§åĬĽ
    0.09
    Activations Density 0.085%

    No Known Activations