© 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. 36663
    Prev
    Next
    INDEX
    Explanations

    names like Leslie or similar

    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
    -0.11
    å¯IJ
    -0.09
    manship
    -0.09
     descargar
    -0.09
    urally
    -0.09
    çĺ¾
    -0.09
    èĩ¾
    -0.09
    istr
    -0.09
    /animations
    -0.08
    龸
    -0.08
    POSITIVE LOGITS
    ogle
    0.10
    éĻ¬
    0.10
    elt
    0.10
    cip
    0.10
    oom
    0.09
    é¢ı
    0.09
    ann
    0.09
     Crown
    0.09
    زÙĦ
    0.09
     gÅĤów
    0.09
    Activations Density 0.005%

    No Known Activations