© 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. 8053
    Prev
    Next
    INDEX
    Explanations

    extradition, restitution, retribution

    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
    kie
    -0.10
    WC
    -0.09
    swer
    -0.09
    为ä¹ĭ
    -0.09
    woord
    -0.09
    è¸Ĭ
    -0.09
    æ®Ĩ
    -0.09
    ỡ
    -0.08
     clip
    -0.08
    å¿Ŀ
    -0.08
    POSITIVE LOGITS
    åħĭæĸ¯
    0.09
    çĽİ
    0.09
     Oliv
    0.09
    lander
    0.09
    eling
    0.08
    edo
    0.08
    aye
    0.08
    el
    0.08
    _performance
    0.08
    olas
    0.08
    Activations Density 0.002%

    No Known Activations