© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36777
    Prev
    Next
    INDEX
    Explanations

    recall, remember, or memorable

    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
    æijĺ
    -0.10
    antha
    -0.10
    äºĭåĦ¿
    -0.09
    磾
    -0.09
    çħ§æł·
    -0.09
    raphics
    -0.09
    åħ»èĢģæľįåĬ¡
    -0.09
    å´ĩå°ļ
    -0.09
    Generic
    -0.09
     Baldwin
    -0.08
    POSITIVE LOGITS
    æĿ¯
    0.09
    åįģ大
    0.09
    ä¸ĢæľŁ
    0.09
    ä½ı
    0.09
    oti
    0.09
    ä¸ĬåįĬå¹´
    0.09
     eid
    0.08
    ius
    0.08
     обÑıз
    0.08
    髦
    0.08
    Activations Density 0.009%

    No Known Activations