© 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. 8434
    Prev
    Next
    INDEX
    Explanations

    back in or back on

    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
    åĮĻ
    -0.09
    åħ¬æŃ£
    -0.09
    nist
    -0.09
    èĭ±æīį
    -0.09
    æĭ³å¤´
    -0.08
    å¦Ĥä½ķåİ»
    -0.08
    è´ŀ
    -0.08
     further
    -0.08
    æĨ¾
    -0.08
    åĺĺ
    -0.08
    POSITIVE LOGITS
    лан
    0.09
    åĨ³å®ļ
    0.09
    ãģ«æĪ»
    0.09
    åķ¤
    0.09
    ç§ij室
    0.08
    è¯¾æľ¬
    0.08
    åľºä¸Ĭ
    0.08
    以æĿ¥
    0.08
    /root
    0.08
    æĺ¾å¾Ĺ
    0.08
    Activations Density 0.014%

    No Known Activations