© 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. 20460
    Prev
    Next
    INDEX
    Explanations

    presenting a positive face

    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
    ä¹IJ趣
    -0.09
    etic
    -0.08
    FREE
    -0.08
    athy
    -0.08
    itat
    -0.08
    pedia
    -0.08
    ä¸įå°½
    -0.08
    ä¸ī次
    -0.08
    UCH
    -0.08
    éĻį
    -0.08
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.12
    è¿Ļ对
    0.11
    çļĦä¸ĢéĿ¢
    0.10
    ä¸Ģåī¯
    0.10
    pst
    0.10
    éĿ¢çĽ®
    0.09
    æĬĹçĻĮ
    0.09
    个æĢ§
    0.09
    åĿļå®ļ
    0.09
     face
    0.09
    Activations Density 0.060%

    No Known Activations