© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    duration followed by event

    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
    ä¸ĢèĪ¬çļĦ
    -0.10
    çļĦéĥ¨åĪĨ
    -0.09
    åĨ¤
    -0.09
    icals
    -0.09
    æ³Ħ
    -0.09
    éģĵ士
    -0.09
    æ´
    -0.09
    å®ħ
    -0.08
    尤为éĩįè¦ģ
    -0.08
    身æĿIJ
    -0.08
    POSITIVE LOGITS
    itre
    0.09
    ly
    0.09
     Goose
    0.09
    é£ĺ
    0.08
    overlap
    0.08
    оде
    0.08
    梳çIJĨ
    0.08
    /is
    0.08
    plans
    0.08
     Balk
    0.08
    Activations Density 0.033%

    No Known Activations