© 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. 37110
    Prev
    Next
    INDEX
    Explanations

    resolution analysis

    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
    æIJ¬
    -0.09
     ÑģÑĤо
    -0.09
    éĿ¢çĽ®
    -0.09
    รว
    -0.09
    éķ¿èĢģ
    -0.08
    æ°¸ä¹ħ
    -0.08
    端
    -0.08
    è´£
    -0.08
    å¿ĥè¡Ģ
    -0.08
    èĺ¸
    -0.08
    POSITIVE LOGITS
    å¤ĸ交
    0.10
    ä½łå°±
    0.09
    åį³åı¯
    0.09
    ä¸Ģä¼ļåĦ¿
    0.09
    klär
    0.08
    åĬ«
    0.08
    ä¸Ģä¼ļ
    0.08
     ÑģможеÑĤе
    0.08
    Foreign
    0.08
    尽头
    0.08
    Activations Density 0.033%

    No Known Activations