© 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. 34589
    Prev
    Next
    INDEX
    Explanations

    unparalleled or unmatched excellence

    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
    lam
    -0.10
    顺åºĶ
    -0.09
    gv
    -0.09
    uro
    -0.09
    ional
    -0.09
    åķĨåŁİ
    -0.08
    å¯ħ
    -0.08
    人人éĥ½
    -0.08
    äºķ
    -0.08
    æĻ®éģį
    -0.08
    POSITIVE LOGITS
    ably
    0.13
    ingly
    0.11
    ously
    0.11
    ä¹ĭåľ°
    0.10
    俦
    0.10
    çļĦçĥŃæĥħ
    0.10
    èĭĩ
    0.09
    ÙĪسط
    0.09
     ability
    0.09
    åŁ½
    0.09
    Activations Density 0.006%

    No Known Activations