© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7954
    Prev
    Next
    INDEX
    Explanations

    Gems, haste, chant, miss, St, Tango

    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
    rise
    -0.09
    æĮĤåı·
    -0.09
     vict
    -0.09
     trải
    -0.08
    ãģĮãĤī
    -0.08
    ä¸įçķĻ
    -0.08
    åĵ¥ä¼¦
    -0.08
    dio
    -0.08
    åĬĿ
    -0.08
    æĭĨè¿ģ
    -0.08
    POSITIVE LOGITS
     обоÑĢ
    0.10
    循
    0.10
    åĽ´
    0.09
    WRAPPER
    0.09
    åıijæĮ¥ä½ľçĶ¨
    0.09
    åŃĺéĩı
    0.08
    PING
    0.08
    åIJĦçľģ
    0.08
    æıĴ
    0.08
    èĩªä¸»åĪĽæĸ°
    0.08
    Activations Density 0.040%

    No Known Activations