© 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. 31768
    Prev
    Next
    INDEX
    Explanations

    SPDX-License-Identifier

    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
    åįģäºĮäºĶ
    -0.13
    éĽ¾éľ¾
    -0.13
    éľ¾
    -0.13
    åįģä¸īäºĶ
    -0.12
     Huffington
    -0.12
    奥巴马
    -0.12
    æĸ°å¸¸æĢģ
    -0.10
    ç»ĻåĬĽ
    -0.10
    ä¹IJè§Ĩ
    -0.10
    åįģåħ«å±Ĭ
    -0.10
    POSITIVE LOGITS
    èµĭèĥ½
    0.12
    ä¸ĵçıŃ
    0.11
    ä¾ĽéĶĢ
    0.11
     Tik
    0.10
    大湾åĮº
    0.09
    å°ĨæĮģç»Ń
    0.09
    æī¿
    0.09
    ERA
    0.09
    æĵĺ
    0.09
    åĬłæĮģ
    0.09
    Activations Density 0.775%

    No Known Activations