© 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. 18738
    Prev
    Next
    INDEX
    Explanations

    theoretical Physics and Mathematics

    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
    çķĮçļĦ
    -0.10
    æĴĩ
    -0.09
    ä¸Ńå°ıåŀĭ
    -0.09
     lac
    -0.09
    溯æºIJ
    -0.08
    çĸı
    -0.08
    æŃ»è§Ĵ
    -0.08
     Daily
    -0.08
    èݽ
    -0.08
    elong
    -0.08
    POSITIVE LOGITS
    çłĶ究ä¸Ńå¿ĥ
    0.10
    åħ±å»º
    0.09
    客æ°Ķ
    0.08
    _cent
    0.08
    vertis
    0.08
     Gst
    0.08
     AUTHORS
    0.07
    ç»ĪçĤ¹
    0.07
    举
    0.07
    åĽ½å®¶éĩįçĤ¹
    0.07
    Activations Density 0.363%

    No Known Activations