© 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. 152
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns/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
    LTR
    -0.25
    .cgi
    -0.23
     alike
    -0.22
    FILTER
    -0.21
    åħ¨éĿ¢æıIJåįĩ
    -0.20
     возд
    -0.20
    CACHE
    -0.20
    SCRIPT
    -0.20
    RIX
    -0.20
    goog
    -0.20
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.28
    çĶ¨æĿ¥
    0.23
    owie
    0.23
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.22
     Punch
    0.21
    è¯Ŀ说
    0.21
    æĪĸåħ¶ä»ĸ
    0.21
    icle
    0.21
     pits
    0.21
    _Con
    0.21
    Activations Density 0.934%

    No Known Activations