© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40110
    Prev
    Next
    INDEX
    Explanations

    Copyright (C)

    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
    plevel
    -0.11
    phans
    -0.11
    çĥŃæĥħ
    -0.11
    åѦçĶŁä»¬
    -0.11
    bies
    -0.10
    ä¼ĺçĤ¹
    -0.10
    åĬłæĭ¿
    -0.10
    idal
    -0.10
    èij¡
    -0.10
    è·¯ä¸Ĭ
    -0.10
    POSITIVE LOGITS
    ÑįÑĤомÑĥ
    0.16
    etheless
    0.14
    odore
    0.13
    phalt
    0.13
    tlement
    0.10
    adays
    0.10
    ../../
    0.10
    xiety
    0.09
    ANDARD
    0.09
    bsites
    0.09
    Activations Density 0.833%

    No Known Activations