© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18764
    Prev
    Next
    INDEX
    Explanations

    enriching experiences and opportunities

    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
    subj
    -0.09
    纲
    -0.08
    iox
    -0.08
    èµIJ
    -0.08
    èĦį
    -0.08
    PED
    -0.08
     Fa
    -0.08
    èģĮ称
    -0.08
     subj
    -0.08
    elo
    -0.08
    POSITIVE LOGITS
    ä½ĵéªĮ
    0.14
     experiences
    0.12
    æľºä¼ļ
    0.12
     opportunities
    0.12
    ç»ıåİĨ
    0.11
     trải
    0.11
    å®ŀ践活åĬ¨
    0.11
    çļĦç»ıåİĨ
    0.11
    åħ¬çĽĬæ´»åĬ¨
    0.10
    çļĦæľºä¼ļ
    0.10
    Activations Density 0.097%

    No Known Activations