© 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. 7770
    Prev
    Next
    INDEX
    Explanations

    lived experiences

    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
    empor
    -0.09
    åķĦ
    -0.09
    å¯Ĵ
    -0.08
    6
    -0.08
    5
    -0.08
    æ¯ħåĬĽ
    -0.08
    9
    -0.08
    æĸ°å¹´
    -0.08
    åıijåħī
    -0.08
    åĩłå¼ł
    -0.08
    POSITIVE LOGITS
    UTH
    0.10
    å±Ļ
    0.09
    æ·±åĪĩ
    0.09
    èĶ½
    0.09
     Identity
    0.09
    _BOTH
    0.09
    çĶŁåij½çļĦ
    0.09
    缨
    0.09
    深深
    0.09
    åŁļ
    0.09
    Activations Density 0.101%

    No Known Activations