© 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. 27619
    Prev
    Next
    INDEX
    Explanations

    ftp, server, or France

    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°Ĩ以
    -0.08
    ä½ĵçİ°åľ¨
    -0.08
     Currently
    -0.08
    åIJĦç±»
    -0.08
    łéĻ¤
    -0.08
    elm
    -0.08
    å¾Ĺ罪
    -0.08
    etxt
    -0.08
    ald
    -0.08
    ibern
    -0.08
    POSITIVE LOGITS
    å±ħçĦ¶
    0.09
    å¾ĪæŃ£å¸¸
    0.09
    幸ç¦ıæĦŁ
    0.09
    æĪĸèĢħåħ¶ä»ĸ
    0.09
     GRAT
    0.09
    åħ±äº§åħļåijĺ
    0.08
    åħ¸åŀĭçļĦ
    0.08
    tank
    0.08
    éķ¿å¯¿
    0.08
    社ä¼ļåĮĸ
    0.08
    Activations Density 0.613%

    No Known Activations