© 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. 5013
    Prev
    Next
    INDEX
    Explanations

    routes caravans travelers

    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
    èĢģæŧå°ıåĮº
    -0.10
    èºį
    -0.10
    athlon
    -0.10
    å³»
    -0.10
    rtle
    -0.09
    大èĩªçĦ¶
    -0.09
    å¢ŀéĩı
    -0.09
    æ³³
    -0.09
    å¯Łçľĭ
    -0.09
    认è´Ń
    -0.09
    POSITIVE LOGITS
    è´¸æĺĵ
    0.11
    æĹħè¡Į
    0.10
     caravan
    0.10
     travelers
    0.10
    å¼Ģæĭĵ
    0.09
    æĹħéĢĶ
    0.09
    åķĨè´¸
    0.09
    åķĨ
    0.09
    è¿IJè¾ĵ
    0.09
    绾
    0.09
    Activations Density 0.061%

    No Known Activations