© 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. 39639
    Prev
    Next
    INDEX
    Explanations

    locations following 'in' or 'at'

    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
    éĤ£ä¸ĢåĪ»
    -0.10
    ä»ĸ们æĺ¯
    -0.10
    ä½Ĩä»ĸ们
    -0.10
     ÑĢа
    -0.10
    ä»Ģä¹Īåı«
    -0.10
    åĽłä¸ºä»ĸ们
    -0.10
    éĤ£æ®µ
    -0.09
    ä¸įå¿ħ
    -0.09
    ä¸ºæľŁ
    -0.09
     поÑĤомÑĥ
    -0.09
    POSITIVE LOGITS
    еннаÑı
    0.09
    izr
    0.09
    ushman
    0.08
    ãĢģãĢģ
    0.08
    dist
    0.08
    åĪĻ
    0.08
    кова
    0.08
    Tomorrow
    0.08
    rientation
    0.08
    strap
    0.08
    Activations Density 0.347%

    No Known Activations