© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35680
    Prev
    Next
    INDEX
    Explanations

    online shopping or services

    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
    æĸĩåĮĸåĴĮ
    -0.10
    reamble
    -0.10
    hait
    -0.09
    _suite
    -0.09
    ardin
    -0.09
    .Linked
    -0.09
    Href
    -0.09
    ising
    -0.09
     Contributor
    -0.08
    ecast
    -0.08
    POSITIVE LOGITS
    大åħ¨
    0.10
    å¦ĩ
    0.09
    å¤ļå°ijéĴ±
    0.09
    ä¸ĭéĿ¢æĪij们
    0.09
    ç¦ģ
    0.08
    为广大
    0.08
    è®®
    0.08
    ÙĨاÙĨ
    0.08
    èĮĥ
    0.08
     conting
    0.08
    Activations Density 0.284%

    No Known Activations