© 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. 358
    Prev
    Next
    INDEX
    Explanations

    slides and presentations

    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
    磼
    -0.25
    .toInt
    -0.24
     commodities
    -0.24
    -wsj
    -0.24
     Guaranteed
    -0.23
    Serialized
    -0.23
    Serialization
    -0.23
    æµĩ
    -0.23
    à¤ĺ
    -0.23
     Newsp
    -0.23
    POSITIVE LOGITS
     PowerPoint
    0.46
     slides
    0.43
     presentation
    0.41
     presentations
    0.41
    slides
    0.38
    .slides
    0.38
     slideshow
    0.36
     slide
    0.36
    å¹»
    0.35
    æ¼Ķ讲
    0.35
    Activations Density 0.021%

    No Known Activations