© 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. 57044
    Prev
    Next
    INDEX
    Explanations

    pa followed by specific words

    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
    ested
    -0.10
    ORS
    -0.10
    aires
    -0.10
    coles
    -0.10
    naires
    -0.09
    ãĤĥ
    -0.09
    à¨Ĩ
    -0.09
    Ø·ÙĬع
    -0.09
    大åѦæ¯ķä¸ļ
    -0.09
    ãģ¾ãģĤ
    -0.09
    POSITIVE LOGITS
    ience
    0.09
    Ùĭ
    0.09
    quette
    0.09
    eted
    0.09
    our
    0.08
    urpose
    0.08
    ä¹ĭä½Ļ
    0.08
    iente
    0.08
    eut
    0.08
    aking
    0.08
    Activations Density 0.024%

    No Known Activations