© 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. 31554
    Prev
    Next
    INDEX
    Explanations

    offerings

    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
    ìĶ¨
    -0.09
    walker
    -0.09
    fur
    -0.09
    _matched
    -0.09
    ìĦł
    -0.08
    空æ°Ķ
    -0.08
    èĴ¿
    -0.08
    èĪį
    -0.08
    ardin
    -0.08
    èĬĤèĥ½çݯä¿Ŀ
    -0.08
    POSITIVE LOGITS
    åľ¨ç½ij绾
    0.09
    è¿Ļè¾¹
    0.09
    оÑĢа
    0.09
    ãĤĵãģª
    0.09
    åħ¬å®īå±Ģ
    0.09
    .$.
    0.08
    æīĢä»¥åľ¨
    0.08
    owing
    0.08
    æĿ¥èĩªäºİ
    0.08
    åľĪåŃIJ
    0.08
    Activations Density 0.013%

    No Known Activations