© 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. 22030
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and "time"

    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
    KeySpec
    -0.08
    washer
    -0.08
    itest
    -0.08
    èĵĦ
    -0.08
    antine
    -0.08
    ivism
    -0.08
    itta
    -0.08
    ä¼ĺåħĪ
    -0.08
    æĢ»æĬķèµĦ
    -0.08
    çģ¯ç¬¼
    -0.08
    POSITIVE LOGITS
    第ä¸ī次
    0.16
    åĨįä¸Ģ次
    0.15
    åĨį次
    0.14
    第äºĮ次
    0.14
    again
    0.13
    åıĪä¸Ģ次
    0.13
     again
    0.12
    ä¸Ģéģį
    0.11
    åĨį度
    0.11
     Again
    0.10
    Activations Density 0.044%

    No Known Activations