© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51998
    Prev
    Next
    INDEX
    Explanations

    Lord, Lords, Commons, Peer, Baron

    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
    æį
    -0.10
    æ´ĹèĦ¸
    -0.10
    åĤ¬
    -0.10
    渲
    -0.09
    lien
    -0.08
    Classes
    -0.08
    =date
    -0.08
    èĤŁ
    -0.08
    _cust
    -0.08
    .Hit
    -0.08
    POSITIVE LOGITS
    éĺ´éĺ³
    0.10
    å»·
    0.10
    ckt
    0.09
    éŀij
    0.09
    ä¸į认è¯Ĩ
    0.09
    gue
    0.08
    大楼
    0.08
    oni
    0.08
    ìĨĮ
    0.08
    è´µæĹı
    0.08
    Activations Density 0.082%

    No Known Activations