© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19815
    Prev
    Next
    INDEX
    Explanations

    grocery stores and related items

    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
    abric
    -0.09
    å±Ī
    -0.09
    é¢Ĭ
    -0.08
    æ¯ħåĬĽ
    -0.08
    ä¼ļéķ¿
    -0.08
    âĨ³
    -0.08
    æ½Ń
    -0.08
    amax
    -0.08
    orm
    -0.08
    quer
    -0.08
    POSITIVE LOGITS
    yard
    0.09
    ods
    0.09
    eur
    0.08
    enter
    0.08
    жив
    0.08
     manh
    0.08
    侧ç»ĵæŀĦæĢ§
    0.08
    sit
    0.08
    annis
    0.08
    /utility
    0.08
    Activations Density 0.002%

    No Known Activations