© 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. 37074
    Prev
    Next
    INDEX
    Explanations

    list item markers

    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
    ä¸įæ¸ħ
    -0.09
    è°Ī论
    -0.09
    æ°
    -0.09
    landır
    -0.09
    çĶ¨æĪ·æıIJä¾Ľ
    -0.09
    PropertyParams
    -0.09
    渡
    -0.09
    ä¸Ģ个æĸ°çļĦ
    -0.09
    [url
    -0.08
    виÑĤ
    -0.08
    POSITIVE LOGITS
    ç½ħ
    0.09
    ä¸ĭå·´
    0.08
     likely
    0.08
    à¹Ģà¸ĸ
    0.07
    çİĽä¸½
    0.07
    çĽ¸ä¿¡å¤§å®¶
    0.07
    åı¬åĶ¤
    0.07
    èĮ§
    0.07
    ãģĿãģĹãģ¦
    0.07
    çħ¦
    0.07
    Activations Density 0.893%

    No Known Activations