© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37077
    Prev
    Next
    INDEX
    Explanations

    art and artwork

    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
    çİĭèĢħ
    -0.09
    xing
    -0.09
    æĭĸæ¬ł
    -0.08
    ãģ¹ãģį
    -0.08
    TreeNode
    -0.08
    heim
    -0.08
    vell
    -0.08
    ãĥĿãĥ³
    -0.08
    åıªåī©
    -0.08
    rong
    -0.08
    POSITIVE LOGITS
    abei
    0.09
    åŃ£
    0.09
    æķ´æķ´
    0.09
    ewn
    0.09
    禽
    0.09
    çĦĵ
    0.08
    åIJĦæł·
    0.08
    iveness
    0.08
    icter
    0.08
    clinic
    0.08
    Activations Density 0.015%

    No Known Activations