© 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. 55960
    Prev
    Next
    INDEX
    Explanations

    pretty [positive adjective]

    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
    è¿Ķ乡
    -0.09
    å¬ĸ
    -0.09
    çľīæ¯Ľ
    -0.09
    åĶ®ç¥¨
    -0.09
    actable
    -0.09
    ought
    -0.09
    éģĵ士
    -0.08
    unny
    -0.08
    Creat
    -0.08
     ìĺ¤íŀĪ볤
    -0.08
    POSITIVE LOGITS
    hana
    0.11
    å®Įç¾İçļĦ
    0.10
     pretty
    0.09
    koa
    0.09
    èł¹
    0.09
     stuff
    0.09
    å®Įç¾İ
    0.09
    ê±°
    0.09
    pretty
    0.09
    äºĨåIJ§
    0.09
    Activations Density 0.171%

    No Known Activations