© 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. 34057
    Prev
    Next
    INDEX
    Explanations

    gearing up, preparing, ready, set

    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
    çĬģ
    -0.11
    ç¼¥
    -0.09
    æĺİçŁ¥
    -0.09
    å¾ĢæĿ¥
    -0.09
    æĮ½
    -0.09
    åIJĪãģĦ
    -0.09
    sterol
    -0.08
    __((
    -0.08
    æĮĸ
    -0.08
    woo
    -0.08
    POSITIVE LOGITS
    åĩĨå¤ĩ
    0.22
     ready
    0.20
    åĩĨå¤ĩ好
    0.20
     гоÑĤов
    0.18
    æºĸåĤĻ
    0.17
    ready
    0.16
     prepares
    0.16
     prepare
    0.16
     preparing
    0.16
     Prepare
    0.15
    Activations Density 0.054%

    No Known Activations