© 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. 1572
    Prev
    Next
    INDEX
    Explanations

    An a/an start

    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
    为代表çļĦ
    -0.09
    æ¡©
    -0.08
    inclusive
    -0.08
    ãģıãĤĮ
    -0.07
    为主ä½ĵ
    -0.07
    å·ħ
    -0.07
    æ·Ĩ
    -0.07
    acro
    -0.07
     unp
    -0.07
    راد
    -0.07
    POSITIVE LOGITS
    orem
    0.11
    yna
    0.10
    ÑģÑı
    0.10
    å¸Ĥåľºä¸Ĭ
    0.10
    oret
    0.09
    bsite
    0.09
    onical
    0.09
    _EOL
    0.09
    cona
    0.09
    åİŁåĽłä¹ĭä¸Ģ
    0.09
    Activations Density 0.120%

    No Known Activations