© 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. 37177
    Prev
    Next
    INDEX
    Explanations

    review, look again, reconsider

    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
    åŃº
    -0.09
    èĥ¸æĢĢ
    -0.09
     Schro
    -0.09
    éģ¿ãģij
    -0.09
    è¨
    -0.08
    äºĶ大
    -0.08
    _AURA
    -0.08
    еÑģÑĤв
    -0.08
    æľªç»ıæİĪæĿĥ
    -0.08
    æĿ³
    -0.08
    POSITIVE LOGITS
    审è§Ĩ
    0.13
    修订
    0.11
     reass
    0.11
    éĩįæĸ°
    0.11
    æ£Ģ
    0.10
    review
    0.10
     review
    0.10
    è¯Ħä¼°
    0.10
     reconsider
    0.10
     revision
    0.10
    Activations Density 0.056%

    No Known Activations