© 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. 20844
    Prev
    Next
    INDEX
    Explanations

    generally comparatively

    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
    ä¸įéĢļ
    -0.11
    spy
    -0.10
    è°ħ
    -0.10
    è¯ł
    -0.10
    ä¸įåIJĮäºİ
    -0.09
    称ä¹ĭ
    -0.09
     GANG
    -0.09
    éĥ½åºĶ该
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    çĻ½èī²
    -0.09
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.12
    缸åıį
    0.12
     comparatively
    0.11
    åĪĻæĺ¯
    0.11
    æĽ´åĥıæĺ¯
    0.11
    æĽ´æľī
    0.10
    å®Įåħ¨ä¸įåIJĮ
    0.10
    обоÑĢоÑĤ
    0.10
    åıįåĢĴ
    0.09
    åıįèĢĮ
    0.09
    Activations Density 0.151%

    No Known Activations