© 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. 30414
    Prev
    Next
    INDEX
    Explanations

    Chinese words before English

    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
    lotte
    -0.10
    Ỽ
    -0.10
    顺
    -0.09
    iros
    -0.09
    端æŃ£
    -0.09
    ç¿Ĭ
    -0.09
    leep
    -0.09
    icers
    -0.09
    logen
    -0.09
    oba
    -0.09
    POSITIVE LOGITS
    使ä¹ĭ
    0.17
    使åħ¶
    0.16
    让å®ĥ
    0.14
    以便
    0.10
    以èĩ´
    0.09
    樵
    0.09
    ç¨ĭ度
    0.08
     into
    0.08
    å¹ħ度
    0.08
    ToObject
    0.08
    Activations Density 0.467%

    No Known Activations