© 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. 37167
    Prev
    Next
    INDEX
    Explanations

    that's explanation

    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
    prise
    -0.12
    è¿Ļæł·åģļ
    -0.10
    è¿Ļ对äºİ
    -0.09
    穹
    -0.09
    rtc
    -0.08
    åĩ¡äºĭ
    -0.08
     crud
    -0.08
    ложен
    -0.08
    4
    -0.08
    檩
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.11
    æľĢéĩįè¦ģ
    0.10
    éĵ²
    0.09
    åŀ¸
    0.09
    èĤ¤
    0.09
     Hobby
    0.08
    fun
    0.08
    说åĩºæĿ¥
    0.08
    æľ¬ä¹¦
    0.08
    åı¯æĥ³èĢĮçŁ¥
    0.08
    Activations Density 0.066%

    No Known Activations