© 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. 8104
    Prev
    Next
    INDEX
    Explanations

    government

    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
    çķ´
    -0.09
    çīĪæĿĥå½Ĵ
    -0.09
    çĮĹ
    -0.09
    婵
    -0.09
    icycle
    -0.08
    童年
    -0.08
    æŀľæ±ģ
    -0.08
     Abr
    -0.08
    å±±åºĦ
    -0.08
    rete
    -0.08
    POSITIVE LOGITS
    寡
    0.10
    ç²¾èĭ±
    0.10
    å¨ĺ
    0.10
    èµ°åİ»
    0.09
     polys
    0.09
    AccessException
    0.09
    oley
    0.09
    оÑĩнÑĭй
    0.09
    -Control
    0.09
     elites
    0.09
    Activations Density 0.034%

    No Known Activations