© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7424
    Prev
    Next
    INDEX
    Explanations

    liberal political discourse

    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
    驾é©Ń
    -0.10
    éŀ
    -0.08
    æĢ§ä»·æ¯Ķ
    -0.08
     Thorn
    -0.08
    çī
    -0.08
    Dup
    -0.08
    _radio
    -0.08
    éĸ
    -0.08
    ono
    -0.08
     smugg
    -0.08
    POSITIVE LOGITS
    强è¡Į
    0.10
    åĢ¡å¯¼
    0.10
    æīĢè°ĵ
    0.10
    æıIJåĢ¡
    0.10
    æīĢè¬Ĥ
    0.09
    ç²īèī²
    0.09
    ç¼
    0.09
    æīĢè°ĵçļĦ
    0.09
    åıijæī¬
    0.09
    æĶ¯
    0.09
    Activations Density 0.107%

    No Known Activations