© 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. 33072
    Prev
    Next
    INDEX
    Explanations

    I following personal 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
    ç»Ŀ
    -0.09
    igs
    -0.09
    allback
    -0.09
    ä¾Ľå¤§å®¶
    -0.09
    为广大
    -0.08
    lick
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    à¸ļาล
    -0.08
    åĨ³
    -0.08
    ç»Ļ大家
    -0.08
    POSITIVE LOGITS
    ulous
    0.10
    viously
    0.09
    æĽ¾
    0.09
    uve
    0.09
    bear
    0.09
    iant
    0.09
    åıĪä¸Ģ次
    0.08
    spb
    0.08
     Mine
    0.08
    iously
    0.08
    Activations Density 0.111%

    No Known Activations