© 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. 20666
    Prev
    Next
    INDEX
    Explanations

    names ending in ana or andra

    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
    UTION
    -0.11
    æ°ijæĶ¿å±Ģ
    -0.11
    apter
    -0.11
    佬
    -0.10
    nowled
    -0.10
    มà¸Ļ
    -0.10
    æ°ijæĶ¿
    -0.10
    ä¿ĿçķĻ
    -0.10
     дело
    -0.10
    ments
    -0.09
    POSITIVE LOGITS
    0
    0.11
    8
    0.10
    عÙĪا
    0.10
    2
    0.09
    3
    0.09
    9
    0.09
    1
    0.09
    4
    0.09
    7
    0.09
    amp
    0.09
    Activations Density 0.039%

    No Known Activations