© 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. 52296
    Prev
    Next
    INDEX
    Explanations

    since + past participle

    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
    æľĢç»Ī
    -0.13
    çİ°åľ¨å·²ç»ı
    -0.12
     Whip
    -0.10
    æѤæŶ
    -0.10
    å½ĵæŶ
    -0.10
    æľĢåIJİ
    -0.10
    åĪ°æŶåĢĻ
    -0.10
    finity
    -0.10
    çªģçĦ¶
    -0.10
    ä¸ĢæŶ
    -0.09
    POSITIVE LOGITS
    ä¹İ
    0.10
    iais
    0.09
    vers
    0.08
    ãĤ
    0.08
    æľīç½ijåıĭ
    0.08
    umat
    0.08
    ward
    0.08
    åį¯
    0.08
     Ñĩего
    0.08
    åģļ好
    0.08
    Activations Density 0.004%

    No Known Activations