© 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. 51930
    Prev
    Next
    INDEX
    Explanations

    population statistics and distribution

    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
    èĢģ人家
    -0.11
    ë¥ł
    -0.10
    iness
    -0.10
     McGr
    -0.09
    带éĺŁ
    -0.09
    ldr
    -0.09
    ãģıãĤĭ
    -0.09
    é²·
    -0.09
    Ħ
    -0.09
    èµĤ
    -0.08
    POSITIVE LOGITS
    lectic
    0.09
    hood
    0.09
     elkaar
    0.09
    lect
    0.08
    ally
    0.08
    èĢģé¾ĦåĮĸ
    0.08
    ÑĪки
    0.08
    rait
    0.08
    æ®Ĩ
    0.08
    acional
    0.08
    Activations Density 0.049%

    No Known Activations