© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    promotional products, marketing materials

    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
    iny
    -0.09
    è¯ļå®ŀ
    -0.09
    èĩªå·±çļĦ
    -0.09
    iders
    -0.09
    éĵº
    -0.08
    ä¹°
    -0.08
    对èĩªå·±
    -0.08
    森
    -0.08
    ä¿Ŀè¯ģéĩij
    -0.08
    ÃŃvel
    -0.08
    POSITIVE LOGITS
    åıijæĶ¾
    0.12
    èµł
    0.12
    ä¾ĽåºĶ
    0.10
    带åĪ°
    0.10
    æĹłåģ¿
    0.10
    ighted
    0.10
    hell
    0.10
    è£ħ
    0.10
    åºĶæĢ¥ç®¡çIJĨ
    0.10
    éħįå¥Ĺ
    0.09
    Activations Density 0.093%

    No Known Activations