© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50369
    Prev
    Next
    INDEX
    Explanations

    human rights and watchdog organizations

    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
    æľ¬ç½ij
    -0.09
     Colt
    -0.09
    æī«é»ij
    -0.09
    åĴ±ä»¬
    -0.09
     usu
    -0.08
    tempt
    -0.08
    oen
    -0.08
    æĪĢ
    -0.08
    emand
    -0.08
    æĦıæĥ³ä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    横
    0.09
    åĿļ
    0.09
    骨头
    0.08
    ende
    0.08
    欢è¿İæĤ¨
    0.08
     Wolf
    0.08
    ä¸Ľä¹¦
    0.08
    ÙĪÙĤ
    0.08
    riet
    0.08
    vb
    0.08
    Activations Density 0.002%

    No Known Activations