© 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. 407
    Prev
    Next
    INDEX
    Explanations

    would followed by auxiliary verbs

    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
    ä¹ĭä½Ļ
    -0.23
    åĴĮå®ĮåĸĦ
    -0.22
    worthy
    -0.21
    illary
    -0.20
    /null
    -0.20
     behalf
    -0.20
    åħµé©¬
    -0.20
    استÙģ
    -0.20
    è¦ģä¸įè¦ģ
    -0.19
    еÑĨ
    -0.18
    POSITIVE LOGITS
    nt
    0.36
    -be
    0.32
    ãģ¹ãģį
    0.30
    ’ve
    0.29
     be
    0.29
    've
    0.28
    /w
    0.27
    iams
    0.27
    æĺ¯ä¸Ģ
    0.27
    /c
    0.26
    Activations Density 0.094%

    No Known Activations