© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8478
    Prev
    Next
    INDEX
    Explanations

    direct

    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¦ģç´§
    -0.10
    /her
    -0.09
    大å±Ģ
    -0.09
    ä¸ĸå®¶
    -0.09
     ÐŁÐ¾Ñĩем
    -0.09
    íĥĪ
    -0.09
    :o
    -0.08
     Lambert
    -0.08
    ÑĨиÑĤ
    -0.08
    ä¸ĵèģĮ
    -0.08
    POSITIVE LOGITS
    ities
    0.12
    ives
    0.11
    -minded
    0.10
    ivity
    0.10
    rices
    0.10
    ness
    0.10
    ively
    0.09
    ÃŃsimo
    0.09
    çļĦãģª
    0.09
    å¹²èĦĨ
    0.09
    Activations Density 0.055%

    No Known Activations