© 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. 21019
    Prev
    Next
    INDEX
    Explanations

    up and out

    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
    æĦı大
    -0.09
    åįı
    -0.09
    archs
    -0.08
    æĪij们å¿ħé¡»
    -0.08
    LinkId
    -0.08
     Kurd
    -0.08
    访
    -0.08
    èŀį
    -0.08
    аÑģÑģ
    -0.08
    adle
    -0.08
    POSITIVE LOGITS
    æĪķ
    0.09
    å¾Īä¸įéĶĻ
    0.09
    nee
    0.09
    ä½Ĩä¹Ł
    0.08
     Pascal
    0.08
    âĶĩ
    0.08
     Pace
    0.08
    heid
    0.08
     QUICK
    0.08
    å¤§åľ°
    0.08
    Activations Density 0.033%

    No Known Activations