© 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. 6954
    Prev
    Next
    INDEX
    Explanations

    liable for damages

    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
    ä»Ģä¹Īæł·
    -0.09
     Pony
    -0.09
    å®ŀè´¨
    -0.08
    çĶŁåĬ¨
    -0.08
    .dt
    -0.08
    uem
    -0.08
    anko
    -0.08
    æ¿Ĵ临
    -0.08
    æľ¬è´¨
    -0.08
    abal
    -0.08
    POSITIVE LOGITS
    åį¤
    0.10
    æĿĤ
    0.10
    ä¸įå®ļ
    0.09
     disproportion
    0.09
    è®®
    0.09
    SingleNode
    0.08
    笨
    0.08
    士
    0.08
     Surprise
    0.08
    unders
    0.08
    Activations Density 0.007%

    No Known Activations