© 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. 9317
    Prev
    Next
    INDEX
    Explanations

    pretending to be

    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
    主æĦı
    -0.10
    æĬł
    -0.09
    ä¾Ħ
    -0.09
    ä¸ĭå·´
    -0.09
    èĩªå®¶
    -0.08
    ãģĦãģĭ
    -0.08
    ç¿ĺ
    -0.08
    èĩªæ²»
    -0.08
    赶紧
    -0.08
    çªł
    -0.08
    POSITIVE LOGITS
    é»ijçĻ½
    0.12
    åĨ°åĨ·
    0.09
    ç´¢åıĸ
    0.08
    æī¿è½½
    0.08
    æĿŁç¼ļ
    0.08
    ç¢İ
    0.08
    åĪº
    0.08
    à®±
    0.08
    è¦Ĩ
    0.08
    æĺ¯æĪij
    0.08
    Activations Density 0.215%

    No Known Activations