© 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. 39259
    Prev
    Next
    INDEX
    Explanations

    April spring season

    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
    åĽ½åºĨ
    -0.12
    åľ£è¯ŀèĬĤ
    -0.12
    å¹´æľ«
    -0.12
     Christmas
    -0.11
    åıĮåįģä¸Ģ
    -0.11
    å¹´ç»Ī
    -0.11
     christmas
    -0.10
    åħĥæŦ
    -0.10
    Christmas
    -0.09
    ä¸Ńç§ĭèĬĤ
    -0.09
    POSITIVE LOGITS
    æĺ¥åŃ£
    0.18
     spring
    0.18
    æĺ¥å¤©
    0.18
    April
    0.17
    æĺ¥é£İ
    0.17
    spring
    0.16
    æĺ¥
    0.16
     April
    0.16
    äºĶæľĪ
    0.15
    ä¸ĢåŃ£åº¦
    0.15
    Activations Density 0.229%

    No Known Activations