© 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. 8926
    Prev
    Next
    INDEX
    Explanations

    offering or providing things

    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
     деле
    -0.12
    говоÑĢ
    -0.10
    èĩ¼
    -0.09
    åijĭ
    -0.09
    arah
    -0.09
    itate
    -0.09
    æĭŃ
    -0.08
    æ¡ĪåŃIJ
    -0.08
    ogh
    -0.08
    è°·
    -0.08
    POSITIVE LOGITS
     kepada
    0.10
    解åĨ³æĸ¹æ¡Ī
    0.09
     glimpse
    0.09
     solutions
    0.09
     ÑĥÑģлÑĥги
    0.09
    iska
    0.09
     insight
    0.08
    磾
    0.08
     guidance
    0.08
    æĬĵæįķ
    0.08
    Activations Density 0.127%

    No Known Activations