© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23096
    Prev
    Next
    INDEX
    Explanations

    persuade or convince

    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
    åĢŁæѤ
    -0.08
    instructions
    -0.08
    _AUX
    -0.08
     orient
    -0.08
     ìķĮìķĦ
    -0.08
    询éĹ®
    -0.08
    便æ°ij
    -0.08
    IFE
    -0.08
     Cra
    -0.08
    lap
    -0.08
    POSITIVE LOGITS
    说æľį
    0.21
     convin
    0.13
     thuyết
    0.12
     convince
    0.11
    åĬ£
    0.11
     rằng
    0.11
     persuade
    0.10
    éļį
    0.10
     convinced
    0.10
     persuasion
    0.10
    Activations Density 0.022%

    No Known Activations