© 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. 49001
    Prev
    Next
    INDEX
    Explanations

    exquisite praise words

    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
    å°ıçĻ½
    -0.09
    ILLE
    -0.09
    æijĨåľ¨
    -0.09
    éĩijå±±
    -0.09
    èĥŃ
    -0.08
    æľīä¸Ģ次
    -0.08
    çłĮ
    -0.08
    вен
    -0.08
    çŁ³èĨı
    -0.08
    иÑĢ
    -0.08
    POSITIVE LOGITS
    åĵī
    0.12
    人æīįåŁ¹åħ»
    0.11
    enza
    0.10
    æ¶Ī
    0.10
    iate
    0.10
    ä¸Ģ群
    0.09
    é¢Ĩ导人
    0.09
    纷
    0.09
     shame
    0.09
    ogo
    0.09
    Activations Density 0.043%

    No Known Activations