© 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. 23506
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to people

    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
    ÑıÑģ
    -0.10
    incoming
    -0.09
    éģĵåħ·
    -0.08
    äºĭåħĪ
    -0.08
    ä¸Ģè¾¹
    -0.08
    è°£
    -0.08
    èĩªçĦ¶æĺ¯
    -0.08
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.07
    客åķĨ
    -0.07
    足足
    -0.07
    POSITIVE LOGITS
    æĪij认为
    0.12
    æĪijè§īå¾Ĺ
    0.11
    wik
    0.11
    æĪijçľĭ
    0.11
    é¢Ĩ导人
    0.11
    æĪijåĸľæ¬¢
    0.10
    代表
    0.10
    äºĮæľŁ
    0.10
    ä¸īæľŁ
    0.09
    åıijéŁ³
    0.09
    Activations Density 0.074%

    No Known Activations