© 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. 37086
    Prev
    Next
    INDEX
    Explanations

    photograph descriptive words

    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
    è¢
    -0.10
     Bes
    -0.10
    åĮ£
    -0.09
    å±Ī
    -0.09
    icc
    -0.09
    èݹ
    -0.09
     Went
    -0.09
     Boeh
    -0.09
    aternity
    -0.09
    yw
    -0.09
    POSITIVE LOGITS
    çĻ»
    0.09
    欲
    0.09
    è²Į
    0.09
    å¤ĸè§Ĥ
    0.09
    åı¯è§ģ
    0.09
    енд
    0.09
    åı¯ä»¥çľĭåĩº
    0.09
     Oral
    0.08
    ENN
    0.08
    æĺĶæĹ¥
    0.08
    Activations Density 0.169%

    No Known Activations