© 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. 5485
    Prev
    Next
    INDEX
    Explanations

    life or lived

    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
    åĿļ
    -0.10
    scr
    -0.09
    angs
    -0.09
    HandlerContext
    -0.08
    æĬĢæľ¯æĶ¯æĮģ
    -0.08
    éĶ²
    -0.08
    essler
    -0.08
    èĩªåĪ¶
    -0.08
    jaw
    -0.08
    åĿĽ
    -0.08
    POSITIVE LOGITS
    çijļ
    0.11
    çĻ¾ç§ij
    0.10
    èī°è¾Ľ
    0.09
    æľīåĩłä¸ª
    0.09
    çļĦè¿ĩç¨ĭ
    0.08
    åłij
    0.08
    éĢıæ°Ķ
    0.08
    athers
    0.08
     Legion
    0.08
    ä¼łå¥ĩ
    0.08
    Activations Density 0.160%

    No Known Activations