© 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. 57450
    Prev
    Next
    INDEX
    Explanations

    democracy and elections

    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
    åĽ´
    -0.09
    æĤłæĤł
    -0.09
    è¡Įåĭķ
    -0.08
    åİĤ
    -0.08
    æĹģ
    -0.08
    éĢĥ
    -0.08
    éªļæī°
    -0.08
    /jav
    -0.08
    fel
    -0.08
    çªģåĽ´
    -0.08
    POSITIVE LOGITS
    çĻ»å±±
    0.08
    æ¯ĶåĪĨ
    0.08
    Ø·ÙĬ
    0.08
    agues
    0.08
    annotate
    0.08
     improbable
    0.08
    éĢī举
    0.08
    åѦä½į
    0.08
    æŶæĬ¥
    0.08
    ä¸ĭä¸Ģ
    0.08
    Activations Density 0.028%

    No Known Activations