© 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. 7862
    Prev
    Next
    INDEX
    Explanations

    locating or finding things

    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
    æĪijçŁ¥éģĵ
    -0.10
    æľ¬ç½ijç«Ļ
    -0.09
    è̽
    -0.09
    åħŃåIJĪ
    -0.09
    fully
    -0.08
    马æĭī
    -0.08
    ereal
    -0.08
    uell
    -0.08
    burn
    -0.08
    Known
    -0.08
    POSITIVE LOGITS
    æī¾åĩĨ
    0.10
    å®ĿèĹı
    0.09
    sources
    0.09
    èϱ
    0.09
    沸
    0.09
    ä½ľèĢħæīĢæľī
    0.09
    /print
    0.09
    OrCreate
    0.09
    符
    0.09
    å¹¶åIJij
    0.08
    Activations Density 0.021%

    No Known Activations