© 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. 49103
    Prev
    Next
    INDEX
    Explanations

    frequency and Hz

    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
    åħ³éŨ
    -0.10
     META
    -0.10
    éĺ»æĮ¡
    -0.09
    æ¡£
    -0.09
    åĪĩåħ¥
    -0.09
    ä¸ĭçıŃ
    -0.09
    æĮ¡
    -0.09
    æѦèѦ
    -0.09
    è¿ŀè¿ŀ
    -0.08
    ç²¹
    -0.08
    POSITIVE LOGITS
    湿
    0.10
     Hum
    0.10
    æ¿ķ
    0.09
    é£İæĻ¯åĮº
    0.09
    åĽĽé¡¹
    0.09
    çłĶ究ä¸Ńå¿ĥ
    0.09
    åįĵ
    0.09
    çĸ²
    0.09
    伤çĹħ
    0.09
     cents
    0.08
    Activations Density 0.054%

    No Known Activations