© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51836
    Prev
    Next
    INDEX
    Explanations

    hypocrisy or inconsistency

    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
    éĻĮçĶŁäºº
    -0.09
    mods
    -0.09
    è¿·
    -0.09
       
    -0.09
    æģ¶
    -0.09
    æ½®
    -0.09
    ungs
    -0.09
    ä¸įç¡®å®ļ
    -0.08
     Malk
    -0.08
    åľ¨è¿ĩåİ»
    -0.08
    POSITIVE LOGITS
    æīĪ
    0.09
    ulous
    0.09
    ity
    0.09
    иÑħ
    0.09
    -minded
    0.08
    çĽİ
    0.08
    atcher
    0.08
    æĢ§çļĦ
    0.08
    ulum
    0.08
    åıĹ访
    0.08
    Activations Density 0.004%

    No Known Activations