© 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. 51839
    Prev
    Next
    INDEX
    Explanations

    probability

    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
    è¯ķæİ¢
    -0.09
     excess
    -0.09
     contag
    -0.09
    iless
    -0.08
    รม
    -0.08
    pler
    -0.08
    å¼ķèµ·äºĨ
    -0.08
     unlimited
    -0.08
    ä¸īåĪĨ
    -0.08
    æľ¬äºº
    -0.08
    POSITIVE LOGITS
    åĩłçİĩ
    0.16
    æ¦Ĥçİĩ
    0.16
     odds
    0.12
     probability
    0.11
    åŁºæķ°
    0.11
    probability
    0.11
    çİĩ为
    0.11
    çĺª
    0.11
    Slim
    0.11
     chance
    0.10
    Activations Density 0.125%

    No Known Activations