© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37866
    Prev
    Next
    INDEX
    Explanations

    geographical names or programming terms

    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
    ikel
    -0.09
    erre
    -0.08
    ä¸įåĩº
    -0.08
    å¯Ħ
    -0.08
     Fab
    -0.08
    erp
    -0.07
    é¹Ń
    -0.07
    Cab
    -0.07
     pret
    -0.07
    饰
    -0.07
    POSITIVE LOGITS
    RARY
    0.11
    shire
    0.10
    积水
    0.10
     bÃłn
    0.10
    ITAL
    0.09
    -leaning
    0.09
    æ²Ļæ¼ł
    0.09
     Airways
    0.09
    嵬
    0.09
    shine
    0.09
    Activations Density 0.003%

    No Known Activations