© 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. 58390
    Prev
    Next
    INDEX
    Explanations

    his or her possessions

    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
    å§Ĭ妹
    -0.08
    cape
    -0.08
    说æĪij
    -0.08
     Local
    -0.08
     threesome
    -0.08
    leta
    -0.08
    à¹Ħà¸Ń
    -0.08
    atrix
    -0.08
    çıĤ
    -0.08
     Tong
    -0.08
    POSITIVE LOGITS
    为主线
    0.11
    ä»ĸçļĦ
    0.11
     character
    0.10
    ä»ĸ对
    0.10
    çļĦæĢ§æł¼
    0.10
    åı°è¯į
    0.10
    æķij人
    0.10
    è§Ĥä¼Ĺ
    0.09
    主线
    0.09
    _character
    0.09
    Activations Density 0.067%

    No Known Activations