© 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. 19039
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns

    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
    _transition
    -0.09
    .bz
    -0.09
    让èĩªå·±
    -0.09
    etrain
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    æij§
    -0.09
    icl
    -0.09
    _servers
    -0.09
    iment
    -0.08
    令人
    -0.08
    POSITIVE LOGITS
    æĺ¨å¤©
    0.09
    æĬij
    0.09
    è°¨
    0.09
    åİ»åģļ
    0.09
    å½¼
    0.08
    å°ĺ
    0.08
    åľ¨ä¸Ģèµ·
    0.08
     Każ
    0.08
    æĿ¥åģļ
    0.08
     Bet
    0.08
    Activations Density 0.022%

    No Known Activations