© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36438
    Prev
    Next
    INDEX
    Explanations

    you / I / we followed by a verb

    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
    è¿Ļä¹Łæĺ¯
    -0.09
    马ä¸Ĭå°±
    -0.09
    å¾Īå¿«
    -0.09
    æģķ
    -0.09
    å¾Ī容æĺĵ
    -0.09
    æ´ĩ
    -0.09
    å¾Īæľīåı¯èĥ½
    -0.09
    -addon
    -0.09
     inferior
    -0.09
    _KIND
    -0.09
    POSITIVE LOGITS
    ullet
    0.10
    ç¡
    0.09
    anus
    0.09
    èģ¿
    0.09
    åĩĢåľŁ
    0.08
    èĥ½åľ¨
    0.08
    说åĪ°è¿ĻéĩĮ
    0.08
    aptcha
    0.08
    OnInit
    0.08
    adel
    0.08
    Activations Density 0.028%

    No Known Activations