© 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. 62557
    Prev
    Next
    INDEX
    Explanations

    conjunctions like or and

    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
    çIJĨ解åĴĮ
    -0.10
    驹
    -0.10
    ä¼ŀ
    -0.09
     Virt
    -0.09
    çĬĬ
    -0.09
    äºĨä¸ĢäºĽ
    -0.09
    é¢Ħæ¡Ī
    -0.09
    vvm
    -0.09
    ãĤĤãģĤãĤĬ
    -0.09
    åįıè°ĥ
    -0.08
    POSITIVE LOGITS
    åIJĦ项
    0.09
    tright
    0.09
     Aren
    0.09
    çľĭèijĹ
    0.08
    -Mail
    0.08
    åIJĦæĸ¹éĿ¢
    0.08
    etc
    0.08
    robe
    0.08
    æī«çłģ
    0.08
    otr
    0.08
    Activations Density 0.234%

    No Known Activations