© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    dotted, distributed, scattered

    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
    éĿ¢å¯¹éĿ¢
    -0.10
    airo
    -0.09
    æĺİæĹ¥
    -0.09
    .compress
    -0.09
    æĢİä¹Ī说
    -0.09
    çªĸ
    -0.09
    åĽ¢éķ¿
    -0.08
    _SUPPORTED
    -0.08
    emale
    -0.08
    å±Ģéķ¿
    -0.08
    POSITIVE LOGITS
    æķ£å¸ĥ
    0.16
     throughout
    0.15
    éģįå¸ĥ
    0.13
     khắp
    0.12
    ä¸ĢäºĮ
    0.12
    çĤ¹ç¼Ģ
    0.12
    åĪĨæķ£
    0.12
    åĪĨå¸ĥåľ¨
    0.12
    åľ°çĤ¹
    0.11
    æķ£
    0.11
    Activations Density 0.063%

    No Known Activations