© 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. 272
    Prev
    Next
    INDEX
    Explanations

    above or below

    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
    flat
    -0.25
    éĺį
    -0.24
    ç§įç±»
    -0.23
    å·®
    -0.23
     flat
    -0.23
    _THREADS
    -0.22
    模å¼ı
    -0.22
    æĸ°åħ´
    -0.22
    è£Ł
    -0.22
    aco
    -0.21
    POSITIVE LOGITS
     depending
    0.28
    åĽłåľ°åĪ¶å®ľ
    0.25
    ewith
    0.24
    èĩªå¦Ĥ
    0.24
    循
    0.24
    <!--[
    0.22
    ä¼´éļıçĿĢ
    0.21
    rah
    0.21
     deserving
    0.21
    åħ¨åĽ½äººå¤§
    0.21
    Activations Density 0.030%

    No Known Activations