© 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. 31509
    Prev
    Next
    INDEX
    Explanations

    op-ed pieces

    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
    çıŀ
    -0.10
    æĢ§çĸ¾çĹħ
    -0.10
    注åĨĮèµĦæľ¬
    -0.09
    orne
    -0.08
    æĺµ
    -0.08
    顾客
    -0.08
    .persist
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    eric
    -0.08
    ä»ĺ
    -0.08
    POSITIVE LOGITS
    ãģĵãģ¨
    0.09
    å¢ĥ
    0.08
    åŃļ
    0.08
    èµ°åħ¥
    0.08
    -worthy
    0.08
    çĶŁæ¶¯
    0.08
    天ä¸ĭ
    0.08
    æĻļéĹ´
    0.08
    æ·¡
    0.08
    oola
    0.08
    Activations Density 0.002%

    No Known Activations