© 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. 50401
    Prev
    Next
    INDEX
    Explanations

    thought I'd

    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
    æĪij认为
    -0.10
    èĥ³
    -0.10
    belie
    -0.09
    è¹Ī
    -0.09
     mainScreen
    -0.09
    .Expect
    -0.09
    çľĭéĩį
    -0.08
    è°Ĵ
    -0.08
    ä¸ĢèĪ¬çļĦ
    -0.08
    æĬ½çĥŁ
    -0.08
    POSITIVE LOGITS
    éĹ®éĹ®
    0.10
    åģļä¸Ģ个
    0.10
    omal
    0.08
    expert
    0.08
    èĢĮå·²
    0.08
    alist
    0.08
    åİ»çľĭçľĭ
    0.08
    åģļä¸ĢäºĽ
    0.08
    è¯ķè¯ķ
    0.08
    ahn
    0.08
    Activations Density 0.048%

    No Known Activations