© 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. 57460
    Prev
    Next
    INDEX
    Explanations

    verbs followed by an infinitive or 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
    宵
    -0.09
    çĸ¯
    -0.09
    æĸ°ä¸ī
    -0.09
    æ³
    -0.09
    å»ĵ
    -0.09
     плоÑħо
    -0.09
    Ñħо
    -0.09
     Rudd
    -0.08
    究
    -0.08
    æĸ°æĺ¥
    -0.08
    POSITIVE LOGITS
     Rao
    0.09
    è¿Ľä¸ĢæŃ¥
    0.09
    æī¿æĭħ
    0.09
    æĸ¹ä¾¿
    0.09
    便äºİ
    0.09
    åį³ä½¿
    0.09
     further
    0.08
    çĶŁæĢķ
    0.08
    jal
    0.08
    æ¯ı次
    0.08
    Activations Density 0.151%

    No Known Activations