© 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. 19406
    Prev
    Next
    INDEX
    Explanations

    eyes, minds, or heart

    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
    quan
    -0.09
    åĪĿ
    -0.09
    aille
    -0.08
    å±Ģéķ¿
    -0.08
    åľ¨ä¸Ģ个
    -0.08
    urt
    -0.08
    对çĿĢ
    -0.08
    ÙĦÙĦ
    -0.08
    ÙĦÙģ
    -0.08
    让人们
    -0.08
    POSITIVE LOGITS
    oke
    0.09
    åĴķ
    0.09
    形象
    0.09
    ä»ĸæĺ¯ä¸Ģ个
    0.09
    å§ĭç»Ī
    0.08
    å¨ģ
    0.08
    精油
    0.08
    çľ¼éĩĮ
    0.08
     Miche
    0.08
     Bernardino
    0.08
    Activations Density 0.026%

    No Known Activations