© 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. 54342
    Prev
    Next
    INDEX
    Explanations

    financial literacy, preparedness, services, gender, medical, education

    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
    åīįèĢħ
    -0.09
    å¾Ĺåĩº
    -0.08
    Nh
    -0.08
    èħķ
    -0.08
    æ¬łç¼º
    -0.08
    ëĦĺ
    -0.08
    lias
    -0.08
    çIJIJ
    -0.08
    ä»Ģä¹Īäºĭæĥħ
    -0.08
    oo
    -0.08
    POSITIVE LOGITS
    æľīåºı
    0.10
    çĤ¹å¤ļ
    0.09
    vens
    0.09
    æķħ
    0.09
    æľīçļĦçݩ家
    0.09
    æĽ´å¥½
    0.08
    _SM
    0.08
     молод
    0.08
     лег
    0.08
    .enumer
    0.08
    Activations Density 0.190%

    No Known Activations