© 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. 8700
    Prev
    Next
    INDEX
    Explanations

    possible or not

    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
    ali
    -0.10
    ought
    -0.09
    çĽ¸å¯¹è¾ĥ
    -0.08
     resent
    -0.08
    unt
    -0.08
    rema
    -0.08
    åŃĺ
    -0.08
    ä¸Ģ举
    -0.08
    éĹº
    -0.08
    åĬłéĢŁ
    -0.08
    POSITIVE LOGITS
    çīŁ
    0.10
    æĸĩåĮĸ交æµģ
    0.10
    æĸĩåĮĸä¼łæĴŃ
    0.09
    履约
    0.09
    æĥ¦
    0.09
    ç»ıèIJ¥æ´»åĬ¨
    0.09
    éĿ¢åīį
    0.09
    èī¾
    0.09
    ç½ijç»ľä¼łæĴŃ
    0.09
    é¦Ķ
    0.09
    Activations Density 0.030%

    No Known Activations