© 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. 37818
    Prev
    Next
    INDEX
    Explanations

    sit, timeouts, out

    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
    -Oct
    -0.10
    顺åĪ©å®ĮæĪIJ
    -0.10
    社ä¼ļæķĪçĽĬ
    -0.10
    .ReadFile
    -0.10
    ANGO
    -0.09
    åľ¾
    -0.09
    é»ijåIJįåįķ
    -0.09
    -delay
    -0.09
    ä¸ĩåĪĨ
    -0.09
    éĢļçķħ
    -0.09
    POSITIVE LOGITS
    4
    0.10
    6
    0.09
    3
    0.09
    ç¿»
    0.09
    9
    0.09
     until
    0.09
     MISS
    0.09
    ä¼ij
    0.09
    æİīäºĨ
    0.09
    æŃĨ
    0.09
    Activations Density 0.020%

    No Known Activations