© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51718
    Prev
    Next
    INDEX
    Explanations

    political influence

    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
    å®ħ
    -0.10
     costing
    -0.10
    даÑĢ
    -0.09
    éľĵ
    -0.09
    æĭį
    -0.08
    罪
    -0.08
     gest
    -0.08
    éģµå¾ª
    -0.08
    主管éĥ¨éŨ
    -0.08
     target
    -0.08
    POSITIVE LOGITS
    å½±åĵįåĬĽ
    0.26
    å½±åĵįåĬĽçļĦ
    0.22
     influence
    0.21
     Influence
    0.19
    è¯Ŀè¯ŃæĿĥ
    0.17
    åľ°ä½į
    0.17
     влиÑı
    0.16
     вли
    0.16
     вла
    0.16
     influential
    0.15
    Activations Density 0.064%

    No Known Activations