© 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. 7887
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    æĪĸèĢħ说
    -0.09
    æ¸IJ
    -0.09
    åħ¨æĺ¯
    -0.09
    olic
    -0.08
    åĿij
    -0.08
    toa
    -0.08
    леÑĤ
    -0.08
    OCI
    -0.08
    å©Ĩ
    -0.08
     PIT
    -0.08
    POSITIVE LOGITS
    æĽ·
    0.09
    çĽijäºĭä¼ļ
    0.09
    miner
    0.08
    çݳ
    0.08
    è¿Ļä¸ĢåĪĩ
    0.08
    iang
    0.08
     Slip
    0.08
     ÑıзÑĭк
    0.08
    为ä¹ĭ
    0.08
    称
    0.08
    Activations Density 0.559%

    No Known Activations