© 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. 17918
    Prev
    Next
    INDEX
    Explanations

    democracy and politics

    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
    erman
    -0.09
     lev
    -0.08
    åѦä¸ļ
    -0.08
    縻
    -0.08
    åŃIJéĩĮ
    -0.08
    patrick
    -0.08
    empl
    -0.07
    ä¹łä¿Ĺ
    -0.07
    utm
    -0.07
    亲çĪ±
    -0.07
    POSITIVE LOGITS
     minded
    0.11
    -minded
    0.11
    è¿Ľç¨ĭä¸Ń
    0.11
    漪
    0.10
    acyj
    0.10
    anism
    0.10
    cko
    0.10
    /social
    0.10
    allee
    0.10
    -leaning
    0.09
    Activations Density 0.015%

    No Known Activations