© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51945
    Prev
    Next
    INDEX
    Explanations

    acid, retinoids, skin care procedures

    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
    éĻ²
    -0.10
    æŁ´
    -0.10
    elage
    -0.09
    磬
    -0.08
    æ°´æºIJ
    -0.08
    ellow
    -0.08
    çĥŁ
    -0.08
    osex
    -0.08
    å®īä¿Ŀ
    -0.08
    å°±çŁ¥éģĵ
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľå®¤
    0.10
    апÑĢ
    0.10
    -git
    0.09
    éħ¸
    0.09
    ä¹Łä¸įæķ¢
    0.09
     Egg
    0.09
    空åīį
    0.09
    çĹĺ
    0.09
    ød
    0.09
    èıģ
    0.08
    Activations Density 0.056%

    No Known Activations