© 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. 34483
    Prev
    Next
    INDEX
    Explanations

    specific character roles

    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
    å¯¹æľªæĿ¥
    -0.09
    éĢŀ
    -0.09
    åĩºéģĵ
    -0.09
    åij½
    -0.09
    åģļçļĦäºĭæĥħ
    -0.09
    sit
    -0.08
    Unlock
    -0.08
    å®ĺ
    -0.08
    éĴķ
    -0.08
    åĩ¡äºĭ
    -0.08
    POSITIVE LOGITS
    ä¼Ĺ
    0.10
     popcorn
    0.09
    ä¸Ģéģį
    0.09
    oland
    0.09
    æIJ¬åĪ°
    0.08
    çľ¾
    0.08
    åħ¨è¿ĩç¨ĭ
    0.08
    éĿŀ常éĢĤåIJĪ
    0.08
    åı¤
    0.08
    çłĶ讨ä¼ļ
    0.08
    Activations Density 0.049%

    No Known Activations