© 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. 20510
    Prev
    Next
    INDEX
    Explanations

    access

    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
     дÑĥÑħ
    -0.10
    åĺ±
    -0.10
    é¼¾
    -0.10
    çĶµçº¿
    -0.09
    undra
    -0.09
    ALAR
    -0.09
    éĺ²çĽĹ
    -0.09
    è¡ĮæĶ¿åĮº
    -0.09
    åĭī强
    -0.09
    æ¹ĸåĮº
    -0.09
    POSITIVE LOGITS
     access
    0.31
    access
    0.24
    ãĤ¢ãĤ¯ãĤ»ãĤ¹
    0.23
    Access
    0.22
     acesso
    0.21
    _access
    0.21
     Access
    0.20
     accessing
    0.20
    -access
    0.19
    .access
    0.19
    Activations Density 0.128%

    No Known Activations