© 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. 31260
    Prev
    Next
    INDEX
    Explanations

    copyright notice and reserved

    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
    è¥Ł
    -0.09
    åįģåĩłä¸ª
    -0.09
    iband
    -0.08
    çħİ
    -0.08
     niche
    -0.08
    ä¼Ĺ
    -0.08
    涨价
    -0.08
    æľªæĪIJ
    -0.08
    bote
    -0.08
    èĬ¹
    -0.08
    POSITIVE LOGITS
    egas
    0.08
    oldem
    0.08
    å®ĺæĸ¹å¾®ä¿¡
    0.08
    dyn
    0.08
    çĽİ
    0.08
    äº¤æĽ¿
    0.08
    æĪij们å¿ħé¡»
    0.07
    ãĥŀãĥ¼
    0.07
    .must
    0.07
    çļĦæŃ¥ä¼IJ
    0.07
    Activations Density 0.021%

    No Known Activations