© 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. 20984
    Prev
    Next
    INDEX
    Explanations

    names and election results

    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
    _hop
    -0.09
     Tus
    -0.09
    é©¿
    -0.09
    ä¸įå¿į
    -0.08
    anvas
    -0.08
    çħ
    -0.08
     grate
    -0.08
    jk
    -0.08
    works
    -0.08
    çļĦ家åºŃ
    -0.08
    POSITIVE LOGITS
    楼主
    0.10
    connector
    0.09
    _META
    0.09
    派人
    0.09
    å½ĵæŶçļĦ
    0.09
    EmptyEntries
    0.09
    åĨ·åĨ·
    0.09
    ðŁĮĪ
    0.09
    ullah
    0.09
    #index
    0.09
    Activations Density 0.037%

    No Known Activations