© 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. 18237
    Prev
    Next
    INDEX
    Explanations

    acknowledgment or receipt

    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
     Affero
    -0.10
     má»ĩnh
    -0.10
    ãģį
    -0.09
    æľĭåıĭ们
    -0.09
    åħ¨å¥Ĺ
    -0.08
    缫
    -0.08
    å»Ĭ
    -0.08
    èģĶåIJĪ
    -0.08
    å¿ĥ仪
    -0.08
    çļĦåIJĦ项
    -0.08
    POSITIVE LOGITS
    Acknowled
    0.13
     acknowledgment
    0.13
     Ack
    0.13
     ACK
    0.13
     acknowledgement
    0.12
    æī¿è®¤
    0.12
    Ack
    0.12
     receipt
    0.12
    认åı¯
    0.12
     acknowled
    0.11
    Activations Density 0.034%

    No Known Activations