© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56082
    Prev
    Next
    INDEX
    Explanations

    lives of or habits of

    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
    åħ¼èģĮ
    -0.09
    çīĪæľ¬
    -0.09
    åł´åIJĪ
    -0.09
    çĦī
    -0.08
    hardt
    -0.08
    mot
    -0.08
    grim
    -0.08
    клÑİÑĩа
    -0.08
    åľºåIJĪ
    -0.08
    è¯įæĿ¡
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.09
     millions
    0.09
     ÑĥÑĩаÑģÑĤ
    0.09
    ä¸Ģ段
    0.08
     those
    0.08
    those
    0.08
    广大群ä¼Ĺ
    0.08
     billions
    0.08
    ä¸Ģç³»åĪĹ
    0.08
    ç¼µ
    0.08
    Activations Density 0.091%

    No Known Activations