© 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. 21077
    Prev
    Next
    INDEX
    Explanations

    stand alone or stand up

    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
    éĵİ
    -0.11
    æĭ³
    -0.09
    çĶŁæĢķ
    -0.09
    oser
    -0.09
    ä¸ĭéĿ¢å°±
    -0.09
    éĢĤåºĶ
    -0.08
    èĢĮéĿŀ
    -0.08
    zon
    -0.08
    (Constructor
    -0.08
    èħķ
    -0.08
    POSITIVE LOGITS
    stand
    0.11
     Stand
    0.10
    Localization
    0.09
    bull
    0.09
    æ»ļ
    0.09
    Stand
    0.09
    æĹ¥ç͵
    0.09
     Kare
    0.08
    still
    0.08
    è°ķ
    0.08
    Activations Density 0.020%

    No Known Activations