© 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. 5094
    Prev
    Next
    INDEX
    Explanations

    most superlative adjectives

    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
    eline
    -0.09
     hart
    -0.09
    èĥ½å¾ĹåĪ°
    -0.08
    èĢį
    -0.08
    çļĦéĤ£ä¸Ģ
    -0.08
    çIJ
    -0.08
    åħį
    -0.08
    mozilla
    -0.08
    iente
    -0.08
     hap
    -0.08
    POSITIVE LOGITS
    éĿŀ常好çļĦ
    0.11
    å¤ļä¹Ī
    0.11
    æŀģåħ¶
    0.10
    arer
    0.10
     ÑģамÑĭй
    0.09
    æŀģ大çļĦ
    0.09
    æĺ¯å¤ļä¹Ī
    0.09
    ä¸įåı¯
    0.09
    åĽłåľ°
    0.09
    æĺ¯æľĢ
    0.09
    Activations Density 0.089%

    No Known Activations