© 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. 9481
    Prev
    Next
    INDEX
    Explanations

    translate, translator

    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
    交代
    -0.10
    Suc
    -0.09
    è¶Ĭå¤ļ
    -0.08
    æİ¥åħ¥
    -0.08
    令人
    -0.08
    peri
    -0.08
    aga
    -0.08
    éªĤ
    -0.08
    æī£
    -0.08
    vak
    -0.08
    POSITIVE LOGITS
    ç¿»è¯ij
    0.17
    .translate
    0.15
    translator
    0.14
    Translator
    0.14
     translator
    0.13
     Translate
    0.13
    translate
    0.13
    .Translate
    0.12
    Translate
    0.12
     translate
    0.12
    Activations Density 0.067%

    No Known Activations