© 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. 54640
    Prev
    Next
    INDEX
    Explanations

    unmatched/unparalleled/unprecedented

    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
    abee
    -0.09
    çĻŀ
    -0.09
    è®Ń
    -0.09
    å´ĸ
    -0.08
    èĵī
    -0.08
    iline
    -0.08
    iske
    -0.08
     Hero
    -0.08
    /items
    -0.08
    åı¸
    -0.08
    POSITIVE LOGITS
    å¸Ĥåľºä¸Ĭ
    0.12
    åľ¨å¸Ĥåľºä¸Ĭ
    0.11
    æĬĬæīĭ
    0.11
     unparalleled
    0.10
    æĶ¾çľ¼
    0.10
    ä¸ļåĨħ
    0.10
    羡
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.09
    åı¤ä»Ĭ
    0.09
    åľ¨åĽ½åĨħ
    0.09
    Activations Density 0.045%

    No Known Activations