© 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. 38151
    Prev
    Next
    INDEX
    Explanations

    multi-lingual negation/possibility

    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
    æľ¬æĿ¥
    -0.08
    iri
    -0.08
    ppy
    -0.08
    æĦıæĢĿæĺ¯
    -0.07
    åħĪåīį
    -0.07
    оÑĩка
    -0.07
    åħ·
    -0.07
     Sher
    -0.07
    ä»ĬåIJİ
    -0.07
    etc
    -0.07
    POSITIVE LOGITS
    åĬłä»¥
    0.13
    edBy
    0.10
    ترÙĪ
    0.09
    åıĺå¾Ĺ
    0.09
    èĢĮæĿ¥
    0.09
    ç»Ħè£ħ
    0.09
    伪è£ħ
    0.09
    .localization
    0.08
    agues
    0.08
    .getSelection
    0.08
    Activations Density 0.056%

    No Known Activations