© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 349
    Prev
    Next
    INDEX
    Explanations

    prices, lot, selected, sleek, foil, rack, bald

    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
     maken
    -0.23
    ORA
    -0.22
     Bringing
    -0.21
    @\
    -0.21
    åŁºäºİ
    -0.21
    fuse
    -0.20
    aim
    -0.20
    ↵      ↵
    -0.20
     repay
    -0.20
    _until
    -0.20
    POSITIVE LOGITS
     occasions
    0.28
    å¹³åı°ä¸Ĭ
    0.23
    izzard
    0.23
    æ¯ĭ
    0.23
     Gow
    0.23
     pools
    0.22
    ä¸ŃåĽ½åı¤ä»£
    0.22
     Sor
    0.22
     backdrop
    0.22
    apa
    0.21
    Activations Density 0.576%

    No Known Activations