© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 63376
    Prev
    Next
    INDEX
    Explanations

    ending or closing operations

    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
    æīįå¹²
    -0.10
    otten
    -0.10
    åıªæĢķ
    -0.09
    è¿ľå¤Ħ
    -0.09
    çļĦå®¶åºŃ
    -0.09
    ron
    -0.09
    ç´§è¿«
    -0.09
    éļIJç§ģ
    -0.09
    çķĪ
    -0.09
    ulum
    -0.08
    POSITIVE LOGITS
    éĢĢåĩº
    0.09
    ä¸įåĨį
    0.09
     officially
    0.09
     mistress
    0.08
    æ·¦
    0.08
    çϾ年
    0.08
     toc
    0.08
     longtime
    0.08
    ä¸įåı¯éģ¿åħį
    0.08
     permanently
    0.08
    Activations Density 0.108%

    No Known Activations