© 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. 5005
    Prev
    Next
    INDEX
    Explanations

    expect, trust, need, enjoy, love

    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
    åijĬ
    -0.10
    åı¸
    -0.10
    ç»ĻåŃ©åŃIJ
    -0.10
    强è¡Į
    -0.09
    ä»»
    -0.09
    笼
    -0.09
    UME
    -0.09
     Ñħа
    -0.09
    è½»è½»åľ°
    -0.09
    åĢĻ
    -0.08
    POSITIVE LOGITS
    acie
    0.09
    æĭ¥æĬ¤
    0.09
    åı¦ä¸Ģ
    0.09
     nat
    0.08
    hek
    0.08
    æĤ¦
    0.08
    误解
    0.08
    æĦıæĥ³ä¸įåĪ°
    0.08
    éī´
    0.08
    御
    0.08
    Activations Density 0.046%

    No Known Activations