© 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. 37831
    Prev
    Next
    INDEX
    Explanations

    consideration of applications

    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
    FORCE
    -0.09
    åı¸
    -0.09
    .WriteAll
    -0.08
    彩票
    -0.08
    æľīäºĽ
    -0.08
    è¦ģåѦä¼ļ
    -0.08
    éĺ²æŃ¢
    -0.08
    ãĤ¢ãĤ¦ãĥĪ
    -0.08
    æĬ¥åĪĬ
    -0.08
     NDEBUG
    -0.08
    POSITIVE LOGITS
    èĢĥèĻij
    0.19
     consideration
    0.19
    èĢĥéĩı
    0.16
    èĢĥæħ®
    0.15
    è¦ģèĢĥèĻij
    0.15
     ÑĢаÑģÑģмаÑĤÑĢ
    0.15
     consider
    0.13
     Consider
    0.13
     considered
    0.13
     considerations
    0.13
    Activations Density 0.086%

    No Known Activations