© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22262
    Prev
    Next
    INDEX
    Explanations

    Airbrush makeup system, laser, device, phone

    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
    礼è²Į
    -0.09
    æ±ł
    -0.09
    èĤĮèĤ¤
    -0.09
    emon
    -0.09
    è¡«
    -0.08
    erus
    -0.08
    æŶè£ħ
    -0.08
    ixin
    -0.08
    æŀ¯
    -0.08
    oge
    -0.08
    POSITIVE LOGITS
    çĶŁäº§è®¾å¤ĩ
    0.12
    ä¸ĵçĶ¨
    0.12
    设å¤ĩ
    0.12
    å·¥åħ·
    0.12
     equipment
    0.11
     equipments
    0.11
    è¨ŃåĤĻ
    0.10
     tools
    0.10
     обоÑĢÑĥд
    0.10
    æĶ¶å½ķ
    0.10
    Activations Density 0.493%

    No Known Activations