© 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. 52102
    Prev
    Next
    INDEX
    Explanations

    sample or example

    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
    Äł
    -0.09
    ÙĬات
    -0.09
     düzen
    -0.09
    vana
    -0.09
    entication
    -0.09
    ymbol
    -0.09
    ä½ĥ
    -0.09
    enticate
    -0.09
    (Keys
    -0.09
    entic
    -0.09
    POSITIVE LOGITS
    hood
    0.10
    å¢Ł
    0.10
    رÙģ
    0.10
    ðŁĮ°
    0.09
    åºĵ
    0.09
    eos
    0.09
    æµij
    0.09
    ationToken
    0.08
    éķ¿å¤§
    0.08
    atic
    0.08
    Activations Density 0.108%

    No Known Activations