© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    persuasion and coercion

    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
     reflecting
    -0.26
    åıįæĺł
    -0.26
    åıįæĺłäºĨ
    -0.25
    reflect
    -0.25
     transitional
    -0.24
     reflective
    -0.23
     clutter
    -0.23
     reflections
    -0.23
     echoes
    -0.23
     reflects
    -0.23
    POSITIVE LOGITS
    说æľį
    0.57
     persuasion
    0.56
     persu
    0.51
     coerc
    0.49
     persuasive
    0.49
     persuade
    0.49
     coercion
    0.45
    诱导
    0.45
    诱
    0.44
     coax
    0.43
    Activations Density 0.094%

    No Known Activations