© 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. 51200
    Prev
    Next
    INDEX
    Explanations

    imperative verbs and calls to action

    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
    åºĨ
    -0.08
     пÑĢог
    -0.08
    ä¾
    -0.08
    _elems
    -0.07
     Prem
    -0.07
    ContextHolder
    -0.07
    :@
    -0.07
     Guid
    -0.07
    çıī
    -0.07
     wee
    -0.07
    POSITIVE LOGITS
    ä¸įè¦ģåĨį
    0.13
    æ¡´
    0.10
    为ä»Ģä¹Īä¸į
    0.10
    è¿Ļä¸ĢåĪ»
    0.09
    æ³ī
    0.09
     СейÑĩаÑģ
    0.09
    éļ¾éģĵ
    0.09
    èĦ¸
    0.09
    å¥Ĺé¤IJ
    0.09
    ç»Ļèĩªå·±
    0.09
    Activations Density 0.054%

    No Known Activations