© 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. 22904
    Prev
    Next
    INDEX
    Explanations

    Republican or Democratic candidates

    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
    çĻ½è¡£
    -0.12
    èıĸ
    -0.09
    cest
    -0.09
    稳
    -0.09
    ature
    -0.09
    æĿµ
    -0.09
    ç°ĭ
    -0.09
    æĪijèĩªå·±
    -0.09
    èĴ¯
    -0.09
    æĩĤ
    -0.09
    POSITIVE LOGITS
    доÑĢ
    0.10
     mó
    0.10
    lector
    0.09
    åľ¨ä¸ŃåĽ½
    0.09
    é¢Ĩ
    0.08
    çļĦ好
    0.08
    retty
    0.08
     dumping
    0.08
    å¤ĦåĪĨ
    0.08
    è¾ŀ
    0.08
    Activations Density 0.022%

    No Known Activations