© 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. 34619
    Prev
    Next
    INDEX
    Explanations

    family members and relations

    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
    æĪijåıĪ
    -0.10
    æĪijçĪ¸
    -0.09
    æĢİä¹ĪåĽŀäºĭ
    -0.09
    客æĪ·æıIJä¾Ľ
    -0.09
    ä¹ĭç±»çļĦ
    -0.09
    æ¼Ķä¹ł
    -0.08
    _ht
    -0.08
    罩
    -0.08
    侪
    -0.08
    ä¹ĭ举
    -0.08
    POSITIVE LOGITS
    è¶ħ强
    0.10
    åıªæľīä¸Ģ个
    0.09
     Testament
    0.09
    管å§Ķä¼ļ
    0.09
    çķĮ
    0.09
    ç¼¢
    0.08
    çĶŁèĤĸ
    0.08
    ç½ij游
    0.08
    idget
    0.08
    çľģæĶ¿åºľ
    0.08
    Activations Density 0.006%

    No Known Activations