© 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. 51810
    Prev
    Next
    INDEX
    Explanations

    monarchs and monarchies

    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
    оваÑĢ
    -0.13
    å»ĵ
    -0.10
    çĪ¹
    -0.10
    andro
    -0.10
    eling
    -0.10
    rios
    -0.09
    é¼ł
    -0.09
    å½ĺ
    -0.09
    è¾ĸåĮº
    -0.09
    ting
    -0.09
    POSITIVE LOGITS
    allee
    0.11
    ic
    0.10
    ystal
    0.09
    èµ·ä¼ı
    0.09
    lam
    0.09
    ues
    0.09
    à¹Į
    0.08
    InternalServerError
    0.08
    ical
    0.08
     Calif
    0.08
    Activations Density 0.005%

    No Known Activations