© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51571
    Prev
    Next
    INDEX
    Explanations

    signaling or signifying

    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
    coat
    -0.08
    .Inject
    -0.08
    ương
    -0.08
    æĻĴ
    -0.08
    æ»´
    -0.08
     Сов
    -0.08
    èħĬ
    -0.08
    å·§
    -0.08
     Seats
    -0.07
    .define
    -0.07
    POSITIVE LOGITS
    æ²ī
    0.10
    éĵ¢
    0.10
    ging
    0.10
    ç¥ŀéĢļ
    0.09
    æĽ´å¤ļçļĦæĺ¯
    0.09
     bulbs
    0.09
    chte
    0.08
    åıĺæį¢
    0.08
    ize
    0.08
    产ä¸ļåįĩ级
    0.08
    Activations Density 0.012%

    No Known Activations