© 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. 37740
    Prev
    Next
    INDEX
    Explanations

    provide information or feedback

    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
    æ¦Ĥè¿°
    -0.09
    Ụ
    -0.08
     пÑĢогн
    -0.08
    å¾Īå¥½åľ°
    -0.08
    æįī
    -0.08
     minded
    -0.08
    硼
    -0.08
    é¼ĵ
    -0.08
    uj
    -0.08
    á»IJ
    -0.08
    POSITIVE LOGITS
    为èĩªå·±
    0.09
    轶
    0.09
    åĬłåĢį
    0.09
    ç»Ļèĩªå·±
    0.09
    resse
    0.09
    dur
    0.09
    说èĩªå·±
    0.09
    aison
    0.09
    ç½¢
    0.08
    身影
    0.08
    Activations Density 0.027%

    No Known Activations