© 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. 8585
    Prev
    Next
    INDEX
    Explanations

    Slashdot, Ellen, specific symbols, technical terms

    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
    edList
    -0.09
    rise
    -0.09
    ives
    -0.09
    udu
    -0.08
    posium
    -0.08
    Unload
    -0.08
    马ä¸Ĭ
    -0.08
     ÑģовеÑĢÑĪен
    -0.08
    atics
    -0.08
    ../../../
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.10
    éľĩæĴ¼
    0.10
    å°±æĺ¯è¿Ļæł·
    0.09
    俪
    0.09
    esktop
    0.09
    sty
    0.09
    acting
    0.09
    ìķł
    0.09
    æľīè¿Ļæł·çļĦ
    0.08
    fur
    0.08
    Activations Density 0.006%

    No Known Activations