© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51919
    Prev
    Next
    INDEX
    Explanations

    seeking answers

    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
    èĻİ
    -0.10
    abric
    -0.09
    èĥ½è¾¾åĪ°
    -0.09
     ÑģÑĦ
    -0.09
    bane
    -0.09
    å±¥
    -0.09
    iaux
    -0.09
    æijĺ
    -0.09
    两次
    -0.09
    abwe
    -0.09
    POSITIVE LOGITS
     answers
    0.15
    çŃĶæ¡Ī
    0.12
     Answers
    0.12
    çļĦçŃĶæ¡Ī
    0.11
    Answers
    0.10
     answered
    0.10
    answers
    0.10
    è¿ĻäºĽéĹ®é¢ĺ
    0.10
    æĽ´å¤ļçļĦ
    0.10
    åĶ¾
    0.09
    Activations Density 0.041%

    No Known Activations