© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7102
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and adverbs

    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
    åī¯éĻ¢éķ¿
    -0.10
    该éĻ¢
    -0.09
    çĥģ
    -0.09
    涨åģľ
    -0.09
    ç¬ŀ
    -0.09
    åģ¶å°Ķ
    -0.09
    è¦ģç´§
    -0.09
    éĻ¢éķ¿
    -0.09
    å·¡è§Ĩ
    -0.08
    åħļçļĦåįģä¹Ŀ
    -0.08
    POSITIVE LOGITS
    èĥ½åģļåĪ°
    0.12
    æ¿ł
    0.09
    åģļä¸įåĪ°
    0.09
    çĿĢåĬĽ
    0.08
    Ùģس
    0.08
    å¾Ģå¾Ģ
    0.08
    ADER
    0.08
    unread
    0.08
     notoriously
    0.08
    ä»¥äººä¸ºæľ¬
    0.08
    Activations Density 0.087%

    No Known Activations