© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2221
    Prev
    Next
    INDEX
    Explanations

    opportunism, hypocrisy, greed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ç»Ħç»ĩå¼Ģå±ķ
    -0.24
     misses
    -0.24
    ()->
    -0.23
     miss
    -0.23
    imilar
    -0.23
    miss
    -0.22
    宫
    -0.22
    åı²ä¸ĬæľĢ
    -0.22
    CAF
    -0.21
     impacting
    -0.21
    POSITIVE LOGITS
    å»īä»·
    0.29
     Suddenly
    0.27
    è°Ħ
    0.27
     suddenly
    0.27
    忽
    0.26
    èĩŃ
    0.26
    Suddenly
    0.26
     hypocrisy
    0.24
    è¿ĻæŶåĢĻ
    0.24
     greed
    0.24
    Activations Density 0.089%

    No Known Activations