© 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. 11127
    Prev
    Next
    INDEX
    Explanations

    first, go, or 1st

    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
    adic
    -0.09
    çĥŃéĩı
    -0.09
    brush
    -0.08
    骨头
    -0.08
    æįı
    -0.08
    æŃ£å½ĵ
    -0.08
    iedo
    -0.08
    ä»ĩ
    -0.08
     Dear
    -0.08
    ä¸Ńåįİ
    -0.08
    POSITIVE LOGITS
    çİĩåħĪ
    0.24
    æľĢåħĪ
    0.17
    æľĢæĹ©
    0.14
    åħĪè¡Į
    0.14
    æĬ¢åħĪ
    0.13
    åħĪ
    0.13
     primero
    0.12
    é¦ĸ家
    0.12
     먼ìłĢ
    0.12
     tiên
    0.11
    Activations Density 0.052%

    No Known Activations