© 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. 49152
    Prev
    Next
    INDEX
    Explanations

    without followed by a noun

    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
    æIJ¬å®¶
    -0.09
    奢
    -0.09
     nowhere
    -0.09
    ä¹ĭ家
    -0.09
    仲
    -0.09
    licative
    -0.09
    ÑģÑĤвенно
    -0.09
    åı£æ°Ķ
    -0.08
    art
    -0.08
    課
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.10
     него
    0.09
    çĢijå¸ĥ
    0.09
    è¿Ļæī¹
    0.09
    åıĸåĨ³
    0.08
     them
    0.08
    æľĢåIJİä¸Ģ次
    0.08
    çļĦæĶ¯æĮģ
    0.08
    ASC
    0.08
    è¸ıä¸Ĭ
    0.08
    Activations Density 0.037%

    No Known Activations