© 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. 11974
    Prev
    Next
    INDEX
    Explanations

    AAA classifications

    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
    æŃ£è§Ħ
    -0.09
    _AF
    -0.08
     behalf
    -0.08
     Kay
    -0.08
    çĻ½è¡£
    -0.08
    深深çļĦ
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    ä¸įäºĨ
    -0.08
    å·²ä¹ħçļĦ
    -0.08
    çļĦä¸Ģ大
    -0.08
    POSITIVE LOGITS
    ä¸ľæµ·
    0.09
    æĺ¨
    0.09
    igion
    0.08
    èģĶèµĽ
    0.08
    碲
    0.08
    åİĨåı²æĸ°
    0.08
    omap
    0.08
     Wheeler
    0.08
    ä¼łéĢĴ
    0.08
    urls
    0.08
    Activations Density 0.006%

    No Known Activations