© 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. 37361
    Prev
    Next
    INDEX
    Explanations

    extract

    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
    ä½ıäºĨ
    -0.10
    åĬĪ
    -0.09
    PUTE
    -0.09
    PAD
    -0.09
    unded
    -0.09
    urette
    -0.09
    åģĩ
    -0.09
    _CLI
    -0.08
     Written
    -0.08
    listed
    -0.08
    POSITIVE LOGITS
    æıIJåıĸ
    0.10
    èIJĥ
    0.10
    æĹ¶è¡¨ç¤º
    0.09
    æıIJçĤ¼
    0.09
    ä¿Ŀå®Ī
    0.09
    çį¬
    0.08
    èijĨ
    0.08
    FromClass
    0.08
    å±ł
    0.08
    æĮ¤
    0.08
    Activations Density 0.138%

    No Known Activations