© 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. 8909
    Prev
    Next
    INDEX
    Explanations

    together or in combination

    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
    æĹłåħ³
    -0.09
     UNITY
    -0.08
    bits
    -0.08
    éĺľ
    -0.08
    èļ¶
    -0.08
     umb
    -0.08
    Unity
    -0.08
     docs
    -0.08
    è°ĥåĬ¨
    -0.08
    èĢĮåIJİ
    -0.07
    POSITIVE LOGITS
    æIJŃéħį
    0.20
    éħįåIJĪ
    0.18
    éħįå¥Ĺ
    0.14
    ä¸İåħ¶ä»ĸ
    0.14
    ä¸Ģèµ·
    0.13
    æIJŃæ¡£
    0.13
     conjunction
    0.11
     phá»iji
    0.11
     together
    0.11
    åľ¨ä¸Ģèµ·
    0.11
    Activations Density 0.170%

    No Known Activations