© 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. 51552
    Prev
    Next
    INDEX
    Explanations

    farm

    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
    çļĦèµĦéĩij
    -0.10
    çī§åľº
    -0.09
    pta
    -0.09
    èµĦéĩij
    -0.09
    骡
    -0.09
    èĢį
    -0.09
    è´¢åĬĽ
    -0.09
    纱
    -0.09
    æĶ¿
    -0.09
    åĨħ马
    -0.09
    POSITIVE LOGITS
    çĵľ
    0.12
    éĻ¢
    0.10
    æĶ¶èİ·
    0.09
     ÑĢа
    0.08
    _tw
    0.08
     produce
    0.08
    .scala
    0.08
     пÑĢид
    0.08
    æŀ¶
    0.08
    忸
    0.08
    Activations Density 0.026%

    No Known Activations