© 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. 52376
    Prev
    Next
    INDEX
    Explanations

    propaganda and slogan

    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
    èĭ«
    -0.11
    åŃIJéĩĮ
    -0.11
    áŁĴáŀ
    -0.10
    åľŃ
    -0.10
    PCS
    -0.09
    noch
    -0.09
    ogl
    -0.09
    ë¡Ŀ
    -0.09
    ings
    -0.09
    ç¾¹
    -0.09
    POSITIVE LOGITS
    eur
    0.09
     YY
    0.08
    uros
    0.08
    åı£åı·
    0.08
    æĢ§å¼º
    0.08
    åijĺ
    0.08
    emap
    0.08
    erring
    0.08
    liner
    0.08
     vessel
    0.08
    Activations Density 0.005%

    No Known Activations