© 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. 55026
    Prev
    Next
    INDEX
    Explanations

    life and lives

    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
    åľ¨ä»ĸ
    -0.11
    å¸ĥæĭī
    -0.10
    æľªæĿ¥çļĦ
    -0.10
    addError
    -0.10
    æ°´ä¸Ń
    -0.10
    以ä¸ĬçļĦ
    -0.10
    Åķ
    -0.10
    åijĬ
    -0.10
    åľ¨ä¼łå¥ĩ
    -0.09
    åľ¨æķ´ä¸ª
    -0.09
    POSITIVE LOGITS
    èĪ«
    0.10
    cape
    0.09
    abouts
    0.08
    ä¾Ķ
    0.08
    大äºĭ
    0.08
    åħ¶ä»ĸåĽ½å®¶
    0.08
    luck
    0.08
    gie
    0.08
    å®ļäºĨ
    0.07
    king
    0.07
    Activations Density 0.073%

    No Known Activations