© 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. 9758
    Prev
    Next
    INDEX
    Explanations

    what happened to

    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
    å½ĵæŶ
    -0.09
    æľīä¸Ģå®ļçļĦ
    -0.09
    æĢİ
    -0.09
    vinc
    -0.08
    æľī人
    -0.08
    æľīä¸Ģå®ļ
    -0.08
    讫
    -0.08
    æĸ¹å¼ıè¿Ľè¡Į
    -0.08
    ADR
    -0.08
    ess
    -0.08
    POSITIVE LOGITS
    è¿ĻæĶ¯
    0.12
    åįģ大
    0.10
     возд
    0.10
    稳åģ¥
    0.09
    lew
    0.09
    åīįåIJİ
    0.09
    强çĥĪ
    0.09
    YTE
    0.09
    ersed
    0.09
    åıĪ好
    0.09
    Activations Density 0.017%

    No Known Activations