© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49027
    Prev
    Next
    INDEX
    Explanations

    stupid, dumb, or silly questions/mistakes/problems

    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
    æ´Ľ
    -0.10
     Copp
    -0.09
    èģĮä¸ļéģĵå¾·
    -0.09
    好è¿IJ
    -0.08
    åĪ°æľŁ
    -0.08
    èµŀåĬ©
    -0.08
    çļĦçĪ¶äº²
    -0.08
    èĻ±
    -0.08
    人士
    -0.08
    ç²¾
    -0.08
    POSITIVE LOGITS
    çĹ´
    0.09
    afx
    0.09
    -looking
    0.09
    лÑı
    0.09
     Fabric
    0.09
    cies
    0.08
    å´ĩæĭľ
    0.08
    encil
    0.08
    åĤ»
    0.08
     Bun
    0.08
    Activations Density 0.039%

    No Known Activations