© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59390
    Prev
    Next
    INDEX
    Explanations

    historical information or dates

    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
    Negative Logits
    æĬĴ
    -0.10
    çĨ¨
    -0.09
    峡谷
    -0.09
    åĬ«
    -0.09
    人æ°ij群ä¼Ĺ
    -0.09
    orges
    -0.09
    _scenario
    -0.09
    ä½Ķ
    -0.09
    arks
    -0.09
    pling
    -0.09
    POSITIVE LOGITS
    liv
    0.09
    èĩªå®¶
    0.08
    åģļçļĦ
    0.08
    åŃĹ第
    0.08
    å½ĵæŶ
    0.08
    家åºŃ
    0.08
    çķ¶æĻĤ
    0.08
    äºĨä¸Ģ份
    0.08
    ä½
    0.08
    ÃĹ
    0.08
    Activations Density 0.068%

    No Known Activations