© 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. 20966
    Prev
    Next
    INDEX
    Explanations

    suan, kane, cane

    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
    æį»
    -0.10
    æĸ¯åŁº
    -0.10
    ski
    -0.10
    most
    -0.10
    lier
    -0.09
    ÙĬØŃ
    -0.09
    isle
    -0.09
    lix
    -0.09
    enth
    -0.09
    nas
    -0.09
    POSITIVE LOGITS
       
    0.12
    uck
    0.10
    è¡Įéķ¿
    0.10
    -être
    0.10
    ìĤ¬íķŃ
    0.10
    /OR
    0.10
    berra
    0.09
     ÑģвÑıзи
    0.09
    unts
    0.08
    opies
    0.08
    Activations Density 0.033%

    No Known Activations