© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21639
    Prev
    Next
    INDEX
    Explanations

    в followed by Russian words

    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
    ussian
    -0.09
    离ä¸įå¼Ģ
    -0.09
     вла
    -0.08
    бин
    -0.08
     DbSet
    -0.08
    ÑģÑĮ
    -0.08
     лиÑĪÑĮ
    -0.08
    vos
    -0.08
    /ws
    -0.08
     vit
    -0.08
    POSITIVE LOGITS
    åıijå±ķä¸Ń
    0.12
    æīĭä¸Ĭ
    0.12
    å®ŀè·µä¸Ń
    0.11
    çĬ¶æĢģä¸ĭ
    0.10
    çݯå¢ĥä¸Ń
    0.10
    озвÑĢаÑī
    0.10
    空æ°Ķä¸Ń
    0.10
    平淡
    0.10
    身ä¸Ĭ
    0.10
    rouw
    0.10
    Activations Density 0.094%

    No Known Activations