© 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. 57920
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    -cur
    -0.10
    æ¾¹
    -0.09
    çĽ¥
    -0.08
    æĶ¸
    -0.08
    å²ĺ
    -0.08
    bol
    -0.08
    åĽłä¸ºä»ĸ们
    -0.08
    éľĸ
    -0.08
    å°¼æĸ¯
    -0.08
    lass
    -0.08
    POSITIVE LOGITS
    ths
    0.10
    åĴĮåıijå±ķ
    0.10
    å¾Ĵ
    0.09
    åĴĮæľįåĬ¡
    0.09
    si
    0.09
    acco
    0.09
    çļĦ身影
    0.08
    æݢ讨
    0.08
    eler
    0.08
    æݢ索
    0.08
    Activations Density 0.016%

    No Known Activations