© 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. 20720
    Prev
    Next
    INDEX
    Explanations

    today's [noun]

    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
    åľ¨åĽ½åĨħ
    -0.10
    spe
    -0.09
    å®Ľ
    -0.08
    缮åīįåĽ½åĨħ
    -0.08
    å½ĵæŶ
    -0.08
    äºĨä¸Ģåı£
    -0.08
    å½ĵä»Ĭ
    -0.08
    å¦Ĥä»Ĭ
    -0.08
    è¿ij代
    -0.08
    eral
    -0.08
    POSITIVE LOGITS
    æĿ¡ä»¶ä¸ĭ
    0.10
    prit
    0.10
    为æŃ¢
    0.10
    人们对
    0.10
     society
    0.10
    ledge
    0.09
    æĪĸå°Ĩ
    0.09
     ÑĢеб
    0.09
    åŁºç¡Ģä¸Ĭ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    Activations Density 0.032%

    No Known Activations