© 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. 19958
    Prev
    Next
    INDEX
    Explanations

    request for explanation

    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
    ucer
    -0.10
    manship
    -0.09
    褫
    -0.09
    lords
    -0.09
    itionally
    -0.09
    çļĦåħ³ç³»
    -0.08
    uth
    -0.08
    cape
    -0.08
    çļĦéģĵçIJĨ
    -0.08
    iken
    -0.08
    POSITIVE LOGITS
    æµij
    0.10
    egis
    0.09
    /mit
    0.09
    ми
    0.09
    大åħ¨
    0.09
    追éĹ®
    0.09
    FragmentManager
    0.09
    碼
    0.09
    人éĥ½
    0.08
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.08
    Activations Density 0.016%

    No Known Activations