© 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. 31908
    Prev
    Next
    INDEX
    Explanations

    persuade or convince others

    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
    åķĨæľº
    -0.09
    assen
    -0.09
    ers
    -0.09
    dek
    -0.08
    æĹłç§ģ
    -0.08
    伤
    -0.08
    åĩłåIJį
    -0.08
    rix
    -0.08
    åĽłä¸ºæĪij
    -0.08
    éĵº
    -0.08
    POSITIVE LOGITS
    说æľį
    0.10
    äºĨå¾Īå¤ļ
    0.10
    ENDOR
    0.09
    ä¸į让
    0.09
    æĪĸèĢħ说
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
    åij¶
    0.09
    ably
    0.09
    ache
    0.09
    äºĨä¸Ģä¸ĭ
    0.08
    Activations Density 0.006%

    No Known Activations