© 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. 20817
    Prev
    Next
    INDEX
    Explanations

    parents', 'parents'' children'

    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
    åģı离
    -0.09
     brides
    -0.09
    æ¡
    -0.09
    ardy
    -0.09
    .Annotations
    -0.08
    嫱
    -0.08
    éĢĥèĦ±
    -0.08
     Dess
    -0.08
    ullo
    -0.08
     Cous
    -0.08
    POSITIVE LOGITS
    åŃ©åŃIJçļĦ
    0.17
    让åŃ©åŃIJ
    0.14
    对åŃ©åŃIJ
    0.14
    èĤ²åĦ¿
    0.14
    åŃ©åŃIJ
    0.14
    ç»ĻåŃ©åŃIJ
    0.13
    çļĦåŃ©åŃIJ
    0.12
    åŃIJ女
    0.12
    åħ»èĤ²
    0.11
    åħĴåŃIJ
    0.11
    Activations Density 0.135%

    No Known Activations