© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 39
    Prev
    Next
    INDEX
    Explanations

    state changes or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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¡ij
    -0.24
    æĺ¯ä»Ģä¹Īåij¢
    -0.23
    åĭĩæ°Ķ
    -0.22
    ernel
    -0.22
    æŁı
    -0.21
    æĢ¯
    -0.21
    uesto
    -0.20
    abee
    -0.20
    .jet
    -0.20
    Destination
    -0.20
    POSITIVE LOGITS
    ä¸İåıijå±ķ
    0.29
    ä¸İåIJ¦
    0.28
    /do
    0.27
    raud
    0.26
    /watch
    0.26
    åĴĮåıijå±ķ
    0.24
     themselves
    0.24
    /not
    0.23
    FilterWhere
    0.23
    çļĦè§Ħå®ļ
    0.23
    Activations Density 0.251%

    No Known Activations