© 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. 35270
    Prev
    Next
    INDEX
    Explanations

    bid

    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
    ä¹°åįķ
    -0.09
    åľ°çľĭçĿĢ
    -0.08
    éģĵè·¯ä¸Ĭ
    -0.08
    ãģĭãĤĤ
    -0.08
    DIC
    -0.08
    oret
    -0.08
     PDT
    -0.08
    èĥĮä¸Ĭ
    -0.08
    æģŃ
    -0.08
    佩
    -0.08
    POSITIVE LOGITS
    ç½ļ
    0.11
    bid
    0.10
     bid
    0.09
    åħį
    0.09
    æĥ¯
    0.08
     Bid
    0.08
     tut
    0.08
    æµ·æ¹¾
    0.08
    _bid
    0.08
    upy
    0.08
    Activations Density 0.030%

    No Known Activations