© 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. 20713
    Prev
    Next
    INDEX
    Explanations

    digital technologies

    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
    ä¼ģä¸ļåıijå±ķ
    -0.09
    æģª
    -0.09
    _pm
    -0.09
    rox
    -0.09
    åĨľèµĦ
    -0.09
    é¬Ĩ
    -0.09
    ä¾
    -0.08
    lint
    -0.08
    åijĬè¯īä½ł
    -0.08
    仲è£ģ
    -0.08
    POSITIVE LOGITS
    ä¿¡æģ¯åĮĸ
    0.19
    æķ°åŃĹåĮĸ
    0.17
    çݰ代åĮĸ
    0.16
    çĶµèĦij
    0.16
     digital
    0.16
    计ç®Ĺæľº
    0.15
     computer
    0.15
     internet
    0.14
     digit
    0.14
    é«ĺç§ijæĬĢ
    0.14
    Activations Density 0.211%

    No Known Activations