© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1126
    Prev
    Next
    INDEX
    Explanations

    prepositions and adverbs

    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
    æ¸İ
    -0.23
    нал
    -0.23
    )p
    -0.22
    ä¹ĥèĩ³
    -0.22
    gr
    -0.21
    åĬ¨åijĺ
    -0.21
     fortune
    -0.21
    (DE
    -0.21
    .part
    -0.20
    æ´»åĬ¨ä¸Ń
    -0.20
    POSITIVE LOGITS
     tightly
    0.25
     mostly
    0.24
     roughly
    0.23
     lightly
    0.23
     slightly
    0.23
    å°ijæķ°
    0.23
     accompanied
    0.23
     usually
    0.23
     fairly
    0.23
    eryl
    0.23
    Activations Density 0.326%

    No Known Activations