© 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. 63289
    Prev
    Next
    INDEX
    Explanations

    seasonings

    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
    ä¸į解
    -0.10
    ikon
    -0.09
    ä»įå°Ĩ
    -0.09
    ëĿ¼ëıĦ
    -0.09
    æ¶Ī失
    -0.09
    èŀįåĮĸ
    -0.09
    ÑĢÑĥд
    -0.09
    æĺİæĺİ
    -0.09
     evangel
    -0.09
    å¤ļãģĦ
    -0.09
    POSITIVE LOGITS
    çļĦåij³éģĵ
    0.08
    èŁł
    0.08
    æĴ¼
    0.08
    amac
    0.08
    Karen
    0.08
    çĪ¸çĪ¸å¦Īå¦Ī
    0.08
    å¥Ķ
    0.08
    .money
    0.08
    _CONSOLE
    0.08
    æīĢéľĢè¦ģ
    0.08
    Activations Density 0.010%

    No Known Activations