© 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. 51766
    Prev
    Next
    INDEX
    Explanations

    being led to

    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
    å¤Ļ
    -0.10
    淹没
    -0.10
    ä»Ģä¹Īéĥ½ä¸į
    -0.10
    æĭ¥æĬ±
    -0.09
    æĬ±
    -0.09
    é¹Ħ
    -0.09
    _secs
    -0.09
    ä¿Ł
    -0.08
    iten
    -0.08
    argout
    -0.08
    POSITIVE LOGITS
    GOR
    0.10
     astr
    0.10
    esty
    0.09
    æİİ
    0.09
    家å±ŀ
    0.08
    кÑĢо
    0.08
    iloc
    0.08
    çıĬ
    0.08
    åĺ¶
    0.08
    槽
    0.08
    Activations Density 0.027%

    No Known Activations